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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 46269
    Prev
    Next
    INDEX
    Explanations

    the names of individuals, especially in a genealogical or biographical context

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

    proper names, numbers, categories

    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
     kaynağından
    -0.35
    IndentedString
    -0.35
    mybatisplus
    -0.34
    enschaften
    -0.33
    "}";
    -0.31
    fromCharCode
    -0.30
    Bronnen
    -0.30
     ύ
    -0.30
     JpaRepository
    -0.29
     spic
    -0.29
    POSITIVE LOGITS
     Infór
    0.59
     Verſ
    0.56
    AddTagHelper
    0.55
    ſelf
    0.54
     informée
    0.54
     насељу
    0.53
    wiſe
    0.53
     saveiro
    0.49
    ſel
    0.48
    ſelben
    0.48
    Activations Density 0.000%

    No Known Activations