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-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 7373
    Prev
    Next
    INDEX
    Explanations

    structured data representations and mathematical expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pronto
    -0.54
    risch
    -0.53
     ioutil
    -0.51
     Республи
    -0.51
    WebControls
    -0.49
    нятие
    -0.49
     Schuster
    -0.49
    StoreMessageInfo
    -0.48
     abbra
    -0.48
    archi
    -0.48
    POSITIVE LOGITS
     Италијани
    0.84
    MigrationBuilder
    0.82
     ModelExpression
    0.68
    Personensuche
    0.67
     beginnetje
    0.63
    出版年
    0.62
     يتيمه
    0.60
     насељу
    0.60
     للمعارف
    0.59
     كومونز
    0.59
    Activations Density 1.020%

    No Known Activations