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 - 32k
    5. 12-GEMMASCOPE-RES-32K
    6. 1732
    Prev
    Next
    INDEX
    Explanations

    key moments in sports events, particularly game-winning actions and critical performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_32k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.71
     AssemblyCulture
    -0.68
     jspb
    -0.66
    providedIn
    -0.65
     AppCompatTheme
    -0.65
    IndentedString
    -0.64
     EconPapers
    -0.63
    ArgsConstructor
    -0.62
    addContainerGap
    -0.61
     BoxDecoration
    -0.60
    POSITIVE LOGITS
    Aktualisiert
    0.53
    tolsó
    0.51
    VersionUID
    0.51
    PhysRevLett
    0.48
    HomeAsUpEnabled
    0.47
     final
    0.47
    breviations
    0.47
     penultimate
    0.47
    ENDING
    0.46
    /'.$
    0.46
    Activations Density 0.051%

    No Known Activations