© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 10459
    Prev
    Next
    INDEX
    Explanations

    specific textual structures or formatting associated with document sections, like opening and closing tags

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.76
    gypti
    -0.66
    帖最后由
    -0.62
    kloped
    -0.61
    bootstrapcdn
    -0.61
     nanop
    -0.60
     ModelExpression
    -0.59
    LayoutInflater
    -0.59
     inkjet
    -0.59
    fscanf
    -0.58
    POSITIVE LOGITS
    </h2>
    0.92
     Audiodateien
    0.80
     bezeichneter
    0.76
    </table>
    0.69
    </h1>
    0.69
    }*/
    0.67
    </h6>
    0.67
     []:
    0.63
     CanadaChoose
    0.60
    </h3>
    0.59
    Activations Density 0.034%

    No Known Activations