Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 20207
    Prev
    Next
    INDEX
    Explanations

    references to calcium-modulating proteins in a biochemical context

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

    modulo 2

    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
    transQ
    -0.55
    AccessorTable
    -0.41
     PyTuple
    -0.40
    ագրություններ
    -0.38
     fortunate
    -0.37
     povezave
    -0.37
    setupUi
    -0.36
    nextProps
    -0.36
    printStackTrace
    -0.36
     cherchés
    -0.35
    POSITIVE LOGITS
    mod
    3.08
    Mod
    2.09
     mod
    2.02
    MOD
    1.94
    mods
    1.91
     Mod
    1.90
    bmod
    1.62
    Mods
    1.60
     mods
    1.59
     MOD
    1.55
    Activations Density 0.004%

    No Known Activations