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. 10-GEMMASCOPE-RES-16K
    6. 4860
    Prev
    Next
    INDEX
    Explanations

    nested structures, particularly brackets and braces within formatted text

    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
    ichan
    -0.67
     suivant
    -0.66
     Meli
    -0.63
     Mehta
    -0.63
     apparaître
    -0.61
     sendiri
    -0.60
     Ghosh
    -0.60
    essége
    -0.60
    Meli
    -0.59
     Tait
    -0.57
    POSITIVE LOGITS
    ?></
    1.08
    </tbody>
    1.02
    awtextra
    1.00
    //</
    0.96
    ."</
    0.94
     Audiodateien
    0.89
    =""></
    0.88
    extAlignment
    0.86
    ).</
    0.86
    .[/
    0.84
    Activations Density 0.118%

    No Known Activations