© 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 - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 5521
    Prev
    Next
    INDEX
    Explanations

    specific abbreviations or acronyms related to scientific or technical contexts

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

    initials ending in w

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    TemporalType
    -0.58
    gei
    -0.53
    retin
    -0.52
    badi
    -0.52
    geli
    -0.51
    quelize
    -0.50
    tis
    -0.49
     انس
    -0.49
    pti
    -0.49
    eric
    -0.49
    POSITIVE LOGITS
     Lw
    1.07
    lw
    1.02
    ew
    0.98
     IW
    0.96
     Iw
    0.95
    fw
    0.92
     Gw
    0.91
     Dw
    0.91
    Lw
    0.91
    iw
    0.91
    Activations Density 0.089%

    No Known Activations