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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4-GEMMASCOPE-RES-16K
    6. 11032
    Prev
    Next
    INDEX
    Explanations

    instances of the beginning of a structured text or document, such as headings or key introductions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.64
    Flint
    -0.60
     Blazers
    -0.59
     MenuView
    -0.58
    cesis
    -0.56
     vela
    -0.56
     gerekir
    -0.55
    mustang
    -0.55
    mesa
    -0.55
    Vikings
    -0.55
    POSITIVE LOGITS
    setcounter
    3.41
    styleType
    0.87
    ScopeManager
    0.85
    enumii
    0.85
    multicolumn
    0.83
     وتسجيلات
    0.81
     CreateTagHelper
    0.81
    protoimpl
    0.79
    NUMX
    0.77
    DockStyle
    0.76
    Activations Density 0.043%

    No Known Activations