© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 5219
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to biological sciences and chemical interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.78
    Jeografia
    -0.75
     BoxFit
    -0.69
    tonode
    -0.67
    ScopeManager
    -0.67
    horts
    -0.67
    таратура
    -0.67
    encodeWith
    -0.66
    MemoryWarning
    -0.66
    alyptus
    -0.66
    POSITIVE LOGITS
     ſhall
    0.56
     Efq
    0.55
     ſhould
    0.52
     iſt
    0.51
     repens
    0.49
    fi
    0.49
     doubtnut
    0.48
     ſche
    0.47
     NUKAT
    0.47
     myſelf
    0.47
    Activations Density 2.772%

    No Known Activations