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. 16-GEMMASCOPE-RES-16K
    6. 8771
    Prev
    Next
    INDEX
    Explanations

    structured data formats or code snippets related to JSON

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code snippets or code-related formatting

    np_acts-logits-general · gemini-2.0-flash

    list items or code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     كومونز
    -0.87
     Offisielt
    -0.81
    __':
    
    -0.76
    IBOutlet
    -0.74
    __":
    
    -0.71
     MainAxisSize
    -0.70
    principalColumn
    -0.65
    glBegin
    -0.60
    ToBounds
    -0.59
    TagMode
    -0.59
    POSITIVE LOGITS
    </strong>
    0.65
    </tbody>
    0.52
    }"
    0.48
    </tr>
    0.47
    」
    0.46
    ).
    0.46
    </sub>
    0.45
    </code>
    0.45
    </em>
    0.45
    ).
    0.44
    Activations Density 0.433%

    No Known Activations