© 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. 15-GEMMASCOPE-RES-16K
    11. 12548
    Prev
    Next
    INDEX
    Explanations

    repeated segments of code or functions in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StructEnd
    -0.69
    PreferredItem
    -0.67
    Vidite
    -0.66
    GeneratedCode
    -0.57
    bisk
    -0.55
     EconPapers
    -0.55
     $_[
    -0.54
    HideFlags
    -0.52
    thentic
    -0.51
    Higgins
    -0.50
    POSITIVE LOGITS
    \{\\
    0.92
    endphp
    0.85
     وتسجيلات
    0.74
     bezeichneter
    0.72
    ]";
    0.67
    ↵
    0.67
    '];
    0.67
    EndInit
    0.66
     CreateTagHelper
    0.65
    ConstraintMaker
    0.65
    Activations Density 0.523%

    No Known Activations