© 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. 16-GEMMASCOPE-RES-16K
    11. 4901
    Prev
    Next
    INDEX
    Explanations

    technical details related to web development and coding references

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

    Code or identifiers within URLs or text

    np_acts-logits-general · gemini-2.0-flash

    sha384 hashes

    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
     виправивши
    -0.63
     noqa
    -0.48
     gewann
    -0.45
    Bab
    -0.45
     initComponents
    -0.43
    IntentFilter
    -0.43
    indexOf
    -0.42
    וויק
    -0.42
    DidChange
    -0.41
     réglage
    -0.40
    POSITIVE LOGITS
     Roskov
    1.05
    Geplaatst
    0.91
    Portale
    0.85
     незавершена
    0.79
    )|^{
    0.75
     يتيمه
    0.75
     Bourgoin
    0.73
     الاطلاع
    0.72
    InputBorder
    0.70
    extAlignment
    0.66
    Activations Density 0.019%

    No Known Activations