© 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. 10-GEMMASCOPE-RES-16K
    6. 11895
    Prev
    Next
    INDEX
    Explanations

    quantities and numeric values in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.80
    httphttps
    -0.80
    expandindo
    -0.67
    Климат
    -0.65
    DeleteBehavior
    -0.64
    thâu
    -0.62
    исленность
    -0.60
    ьаж
    -0.59
    KURZBESCHREIBUNG
    -0.59
    ThroughAttribute
    -0.59
    POSITIVE LOGITS
     }}"></
    0.53
     URB
    0.51
     nakalista
    0.49
     SED
    0.48
    dzi
    0.48
    AccessFile
    0.48
    Backing
    0.47
     Backing
    0.46
    nar
    0.46
     ?>/
    0.46
    Activations Density 1.605%

    No Known Activations