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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1957
    Prev
    Next
    INDEX
    Explanations

    terms related to biological analysis and methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thâu
    -0.36
     Anda
    -0.33
     duide
    -0.33
    wingen
    -0.33
     Investig
    -0.33
    wegg
    -0.32
     شيئ
    -0.31
    OGND
    -0.31
    المناصب
    -0.31
     Eva
    -0.31
    POSITIVE LOGITS
     Administrativna
    0.68
    锈钢
    0.67
    :✨
    0.63
    transQ
    0.62
    queryInterface
    0.56
     AppCompatTheme
    0.55
     JpaRepository
    0.53
    migrationBuilder
    0.53
     referrerpolicy
    0.52
    posedge
    0.52
    Activations Density 1.225%

    No Known Activations