© 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. 20-GEMMASCOPE-RES-131K
    6. 63521
    Prev
    Next
    INDEX
    Explanations

    concepts related to proper structural orientation and installation procedures

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

    make explicit clear progress

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.57
     estekak
    -0.55
     createContext
    -0.54
    principalColumn
    -0.54
     onPostExecute
    -0.53
    المناصب
    -0.53
    ſchen
    -0.52
    ImageContext
    -0.52
    TagHelper
    -0.51
    SequentialGroup
    -0.50
    POSITIVE LOGITS
    可以通过
    0.35
     via
    0.32
     jsPsych
    0.31
    Organizador
    0.31
     Indian
    0.30
    を表
    0.30
    ための
    0.30
     marker
    0.30
    лару
    0.30
    ApiOperation
    0.30
    Activations Density 0.182%

    No Known Activations