© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5294
    Prev
    Next
    INDEX
    Explanations

    specific phrases that indicate purpose or intent

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "To" in various contexts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    infinitive constructions, especially sentence-initial purpose or action clauses introduced by the infinitive marker.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    the word "To" at the beginning of a sentence or clause, particularly when it introduces an infinitive phrase expressing purpose or intention.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ilha
    -0.50
     endregion
    -0.47
    sprzed
    -0.45
    CppMethod
    -0.45
    -------
    -0.44
    verdad
    -0.43
     Ahnung
    -0.42
    .*")]
    -0.41
     Kolle
    -0.40
     Verdad
    -0.40
    POSITIVE LOGITS
     To
    0.82
    To
    0.75
    DrawerToggle
    0.70
    ########.
    0.67
    FunctionFlags
    0.65
    addGroup
    0.63
     surla
    0.59
    makeText
    0.57
     CreateTagHelper
    0.55
    ConstraintMaker
    0.55
    Activations Density 0.129%

    No Known Activations