© 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. 31-GEMMASCOPE-RES-16K
    6. 9528
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their roles in institutional or organizational contexts

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

    phrases indicating someone is speaking in a personal capacity rather than representing an organization or institution.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    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
    ỡng
    -0.32
    muerzo
    -0.32
    Източници
    -0.31
    disposing
    -0.29
    astype
    -0.29
     okol
    -0.29
     Plutarch
    -0.28
     gyhoeddwyd
    -0.28
    kirakan
    -0.28
    cierto
    -0.28
    POSITIVE LOGITS
     representative
    2.83
     representatives
    2.80
     representation
    2.61
    represent
    2.52
    representative
    2.48
     represented
    2.47
     REPRESENT
    2.45
     rappresent
    2.44
     Representatives
    2.42
    代表
    2.41
    Activations Density 0.595%

    No Known Activations