© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 80497
    Prev
    Next
    INDEX
    Explanations

    nouns and phrases related to places and objects

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

    common household objects and places

    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
     Bewußt
    -0.42
    原始内容存档于
    -0.41
    tonode
    -0.40
     مؤرشف
    -0.38
    ⓧ
    -0.37
     brancas
    -0.36
     bezpośrednio
    -0.36
     محفوظة
    -0.35
     rzeczyw
    -0.35
     affatto
    -0.34
    POSITIVE LOGITS
     houſe
    0.71
     ſtate
    0.63
     Eſ
    0.62
    FormTagHelper
    0.61
    ſelves
    0.61
    migrationBuilder
    0.60
     myſelf
    0.60
     ſch
    0.59
    ſelf
    0.58
     ſol
    0.58
    Activations Density 0.111%

    No Known Activations