Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15987
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal terms and conditions

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

    Follows pronouns or possessive adjectives

    np_acts-logits-general · gemini-2.0-flash

    gave medicine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الحره
    -0.56
     indisponible
    -0.56
    setContentType
    -0.55
     <>",
    -0.52
    BufferException
    -0.51
    Hochspringen
    -0.51
    WEBPACK
    -0.50
     تضيفلها
    -0.50
    MethodManager
    -0.49
    ⎨
    -0.49
    POSITIVE LOGITS
    riwal
    0.44
    StructEnd
    0.43
    casila
    0.43
    ględ
    0.40
     disambiguazione
    0.40
     ingres
    0.38
     препратки
    0.38
     connaît
    0.38
     Spitzen
    0.37
     definitivo
    0.37
    Activations Density 3.475%

    No Known Activations