© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 3169
    Prev
    Next
    INDEX
    Explanations

    elements related to coding structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     $=$
    -0.49
     betrek
    -0.45
     Aur
    -0.43
    izze
    -0.43
     Bancroft
    -0.43
     getting
    -0.42
     Aura
    -0.42
     Melinda
    -0.42
     $\&$
    -0.41
     $-$
    -0.40
    POSITIVE LOGITS
    <tr>
    1.93
    </tbody>
    1.45
    ValueStyle
    0.85
     initComponents
    0.74
    TagMode
    0.74
    </table>
    0.74
     الحره
    0.73
    </thead>
    0.73
    enumi
    0.73
    ArgsConstructor
    0.72
    Activations Density 0.002%

    No Known Activations