© 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. 22-GEMMASCOPE-RES-16K
    6. 10144
    Prev
    Next
    INDEX
    Explanations

    specific file path and format settings related to software development

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

    Code or commands related to compiling and linking

    np_acts-logits-general · gemini-2.0-flash

    compilation objects and linking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    posedge
    -0.59
    ี่ยน
    -0.57
    complexType
    -0.56
    findpost
    -0.55
    NOPQRST
    -0.54
     metav
    -0.52
     Wallflower
    -0.52
     onCancelled
    -0.51
     iD
    -0.51
     grooming
    -0.49
    POSITIVE LOGITS
     executable
    0.82
     compiled
    0.81
     runtime
    0.80
     binary
    0.76
     assembly
    0.75
     execu
    0.74
     Assembly
    0.73
     binaries
    0.72
    expandindo
    0.72
    Assembly
    0.68
    Activations Density 0.943%

    No Known Activations