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. 9-GEMMASCOPE-RES-16K
    6. 15452
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands and document formatting elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ustimmung
    -0.70
    kloped
    -0.69
     /\.
    -0.68
     quæ
    -0.67
    modelBuilder
    -0.63
     MonoBehaviour
    -0.63
    |^{
    -0.62
    .[/
    -0.61
    addGap
    -0.61
    Vorlage
    -0.60
    POSITIVE LOGITS
    DoubleQuotes
    1.19
    AddHtmlAttribute
    1.02
    amssymb
    0.98
     BoxDecoration
    0.82
    Clik
    0.78
    CrossRef
    0.77
    ecore
    0.71
    pulumi
    0.71
     initComponents
    0.63
    Sprintf
    0.63
    Activations Density 0.004%

    No Known Activations