© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 6790
    Prev
    Next
    INDEX
    Explanations

    phrases indicating suitability or fit for a specific use or purpose

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

    prepositions and purpose-related words, especially "for" and phrases about intended use.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
     laikā
    -0.41
     efectivos
    -0.37
     informací
    -0.37
     Ahnung
    -0.36
    Autoritní
    -0.36
     historiques
    -0.36
     aikana
    -0.35
     alguno
    -0.35
     mitään
    -0.34
     protectora
    -0.34
    POSITIVE LOGITS
    IUrlHelper
    0.72
    IsMutable
    0.69
    DockStyle
    0.64
    Diweddarwch
    0.61
     Waray
    0.60
     disponibilités
    0.60
     TextInputType
    0.59
    󠁣
    0.57
    tagHelperRunner
    0.57
    KEYCODE
    0.56
    Activations Density 0.248%

    No Known Activations