© 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. 0-GEMMASCOPE-RES-16K
    6. 10051
    Prev
    Next
    INDEX
    Explanations

    terms related to acceptance and adjustment processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xil
    -0.43
     contact
    -0.40
    cyklo
    -0.39
     păr
    -0.39
     cassa
    -0.36
     Age
    -0.35
     presenza
    -0.35
     praktis
    -0.35
    MessageInfo
    -0.33
    readAs
    -0.33
    POSITIVE LOGITS
     adjustment
    0.73
    adjusted
    0.73
    acceptance
    0.70
     adjusted
    0.69
    adjustment
    0.68
     المعيارى
    0.66
     PROTOCOL
    0.65
     Adjustment
    0.65
     Adjusted
    0.64
     accepting
    0.63
    Activations Density 0.229%

    No Known Activations