© 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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10400
    Prev
    Next
    INDEX
    Explanations

    debugging messages related to SSH connections and key management

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

    "debug" in SSH logs

    np_acts-logits-general · gemini-2.0-flash

    debug logging levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    المشاركات
    -0.47
    glTex
    -0.47
     sumpay
    -0.45
     GY
    -0.45
    writeFieldEnd
    -0.44
    ChildScrollView
    -0.44
    ftagPool
    -0.43
     RCP
    -0.42
     Roof
    -0.42
     Acon
    -0.42
    POSITIVE LOGITS
    debug
    1.55
     debug
    1.51
    Debug
    1.41
     Debug
    1.38
     debugging
    1.23
    DEBUG
    1.20
     DEBUG
    1.16
     trace
    1.10
    trace
    1.08
    调试
    1.02
    Activations Density 0.247%

    No Known Activations