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. 2042
    Prev
    Next
    INDEX
    Explanations

    numerical values or data structures associated with programming or technical contexts

    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
    CUR
    -0.68
     official
    -0.67
    tsy
    -0.65
    ustra
    -0.64
     SY
    -0.60
     jo
    -0.60
     CUR
    -0.60
     AX
    -0.59
     Hilda
    -0.59
    DataTo
    -0.59
    POSITIVE LOGITS
    ViewFeatures
    0.97
     nakalista
    0.96
    \{\\
    0.93
    mrow
    0.91
    })).
    0.86
    })));
    0.84
    "])){
    0.83
    /******/
    0.83
    ↵
    0.79
    Personensuche
    0.78
    Activations Density 0.163%

    No Known Activations