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. 11583
    Prev
    Next
    INDEX
    Explanations

    elements of code relating to user interface components or directives

    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
    ↵
    -1.32
    ↵↵
    -1.03
    <eos>
    -1.00
    <tr>
    -0.92
    </tr>
    -0.92
    [toxicity=0]
    -0.83
    ])));
    -0.78
    )]);
    -0.71
    <tbody>
    -0.70
    ↵↵↵
    -0.67
    POSITIVE LOGITS
    ThroughAttribute
    0.74
    Enllaces
    0.72
    DebuggerNonUser
    0.70
    Sucesor
    0.67
     himo
    0.65
     vPvB
    0.64
    InitVars
    0.64
    OrBuilder
    0.62
    XmlAccessType
    0.61
    FunctionFlags
    0.60
    Activations Density 0.103%

    No Known Activations