© 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. 20-GEMMASCOPE-RES-16K
    11. 957
    Prev
    Next
    INDEX
    Explanations

    phrases indicating roles, positions, or titles held by individuals

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

    professional roles and positions in organizations (like president, professor, director, advisor).

    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
     ungkapnya
    -0.33
    -(-
    -0.33
    wpi
    -0.33
    poder
    -0.32
    ngrx
    -0.32
     strikes
    -0.32
    มีความ
    -0.32
     görün
    -0.31
     fleuve
    -0.30
     feel
    -0.30
    POSITIVE LOGITS
     assistant
    0.67
    ftagPool
    0.65
    RTLR
    0.63
     Efq
    0.61
     chief
    0.60
    Rhestr
    0.60
     Chief
    0.60
     deſſen
    0.59
    AutoField
    0.57
     Assistant
    0.57
    Activations Density 0.155%

    No Known Activations