© 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. 18-GEMMASCOPE-RES-16K
    11. 4039
    Prev
    Next
    INDEX
    Explanations

    code constructs related to conditions, data operations, and function calls in programming

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

    Code, files, and audio sessions

    np_acts-logits-general · gemini-2.0-flash

    programming types and settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Filmographie
    -0.66
    expandindo
    -0.66
     Picchu
    -0.58
    deaux
    -0.56
    osaurs
    -0.55
    braio
    -0.55
     Toxicological
    -0.54
    MLLoader
    -0.53
     tartalomajánló
    -0.53
     himo
    -0.52
    POSITIVE LOGITS
    TagMode
    0.73
    HideFlags
    0.68
    FetchType
    0.67
    DockStyle
    0.63
     FetchType
    0.62
     Normdatei
    0.60
     GenerationType
    0.59
    GenerationType
    0.58
    AnchorStyles
    0.58
     TimeUnit
    0.57
    Activations Density 0.535%

    No Known Activations