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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 7533
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to"

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

    "to" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    infinitive phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    お待ちしております
    -0.40
    お
    -0.39
     kaupung
    -0.39
     laikā
    -0.38
     turístico
    -0.37
    guien
    -0.36
    rededor
    -0.35
    nyez
    -0.35
    nolog
    -0.35
    noStroke
    -0.35
    POSITIVE LOGITS
     μην
    0.71
     be
    0.66
     utafitiHapana
    0.65
     the
    0.64
    asts
    0.63
    rungsseite
    0.62
    psy
    0.62
    asting
    0.60
    IntoConstraints
    0.60
     To
    0.59
    Activations Density 1.262%

    No Known Activations