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. 31-GEMMASCOPE-RES-131K
    6. 24394
    Prev
    Next
    INDEX
    Explanations

    action verbs related to achieving, obtaining, or maintaining a state or object

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

    future events, actions, or states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    transQ
    -0.53
    Parcelize
    -0.44
     الدولى
    -0.44
     Reverso
    -0.43
     Remark
    -0.41
    脚注の使い方
    -0.41
     dags
    -0.41
    السكان
    -0.40
    BagLayout
    -0.38
    Remark
    -0.38
    POSITIVE LOGITS
     prochain
    0.64
     soon
    0.63
    きっと
    0.63
     amanhã
    0.58
     will
    0.57
    will
    0.56
     sicuramente
    0.54
     gladly
    0.54
     tomorrow
    0.54
     be
    0.53
    Activations Density 0.109%

    No Known Activations