© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 6558
    Prev
    Next
    INDEX
    Explanations

    topics related to genetic analysis and statistical modeling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HtmlAttribute
    -0.76
    Климат
    -0.72
     AssemblyTitle
    -0.68
    
    -0.67
     surla
    -0.67
    SourceChecksum
    -0.65
    <?,
    -0.65
    ArgsConstructor
    -0.63
    ReusableCell
    -0.60
    parsedMessage
    -0.59
    POSITIVE LOGITS
     HashSet
    0.82
    HashSet
    0.76
    ManyToMany
    0.68
     list
    0.65
     whitelist
    0.64
    rrggbb
    0.61
    whitelist
    0.57
     List
    0.56
     daftar
    0.55
     муніципалі
    0.54
    Activations Density 0.329%

    No Known Activations