© 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. 476
    Prev
    Next
    INDEX
    Explanations

    code structure, particularly related to variable declarations and usage

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

    C# code and related keywords

    np_acts-logits-general · gemini-2.0-flash

    found which

    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
    IntoConstraints
    -0.86
    NewUrlParser
    -0.73
     ProgressDialog
    -0.66
     SqlCommand
    -0.66
     QWidget
    -0.65
    +/**
    -0.64
     opc
    -0.64
     CardView
    -0.64
    CardView
    -0.63
    BorderFactory
    -0.63
    POSITIVE LOGITS
    var
    1.07
     var
    0.73
    string
    0.59
    using
    0.53
    foreach
    0.48
     string
    0.47
     tecniche
    0.46
    tvar
    0.46
    if
    0.45
    modelBuilder
    0.45
    Activations Density 0.047%

    No Known Activations