© 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-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 1284
    Prev
    Next
    INDEX
    Explanations

    occurrences of nested or complex mathematical expressions involving parentheses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }();
    -0.71
     препратки
    -0.69
    τή
    -0.66
    ]-'
    -0.64
    strSql
    -0.64
    -%
    -0.59
    ubel
    -0.59
    bello
    -0.59
     disambiguazione
    -0.58
    afficheront
    -0.58
    POSITIVE LOGITS
    ((
    3.04
     ((
    2.40
    (((
    2.36
    >((
    2.23
    [(
    2.02
    ((((
    2.01
    =((
    1.91
     (((
    1.87
     ((((
    1.77
    )((
    1.73
    Activations Density 0.195%

    No Known Activations