Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 645
    Prev
    Next
    INDEX
    Explanations

    references to structured programming elements or components in code

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

    Code snippets or configuration details

    np_acts-logits-general · gemini-2.0-flash

    Packing Slip, Data Reduction, Render Node, Product Tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     INTERESAR
    -0.69
     الحره
    -0.69
    rungsseite
    -0.66
    featureID
    -0.64
    Vidite
    -0.63
    ViewFeatures
    -0.63
     interni
    -0.61
     ordinaires
    -0.60
     MenuView
    -0.56
    انجليز
    -0.56
    POSITIVE LOGITS
    }>;
    0.74
    }></
    0.68
    \|^{
    0.57
     dAtA
    0.56
    ...@
    0.55
    _
    0.55
    ณฑ
    0.55
    <bos>
    0.55
    })));
    0.54
     exer
    0.53
    Activations Density 0.363%

    No Known Activations