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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 13151
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific coding or structural syntax elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yntaxException
    -0.96
     kaarangay
    -0.95
    зулта
    -0.94
    цездатний
    -0.94
    archiviato
    -0.93
    SharedDtor
    -0.91
    ContentAlignment
    -0.91
     useAppContext
    -0.89
    StoryboardSegue
    -0.87
    UrlResolution
    -0.85
    POSITIVE LOGITS
    scriptcase
    1.08
    nmgp
    0.80
    Pyx
    0.71
    tvguidetime
    0.61
     مرئيه
    0.52
    のが
    0.47
    migrationBuilder
    0.46
    }|\
    0.46
    sc
    0.44
    }?
    0.44
    Activations Density 0.153%

    No Known Activations