© 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. 15-GEMMASCOPE-RES-16K
    6. 3112
    Prev
    Next
    INDEX
    Explanations

    quotes or speech marks in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    %',
    -0.73
    $",
    -0.71
    odotus
    -0.70
    ipheral
    -0.69
    brainly
    -0.69
    $',
    -0.69
    ^(@)
    -0.67
     defaultstate
    -0.67
     Roskov
    -0.67
    جستارهای
    -0.66
    POSITIVE LOGITS
    ].
    0.81
    ).
    0.80
    。
    0.75
    }.
    0.70
    I
    0.68
    .
    0.67
    It
    0.66
    >.
    0.66
    There
    0.65
    )。
    0.65
    Activations Density 0.055%

    No Known Activations