© 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. 20-GEMMASCOPE-RES-16K
    11. 7919
    Prev
    Next
    INDEX
    Explanations

    code snippets related to handling CSV files and data manipulation

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

    Code involving file paths, trees, or databases

    np_acts-logits-general · gemini-2.0-flash

    phase of the action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.64
    AutoresizingMask
    -0.64
     HttpHeaders
    -0.62
     oprot
    -0.60
    ²,
    -0.60
    PostExecute
    -0.59
    AndEndTag
    -0.58
     FetchType
    -0.56
    ServletException
    -0.56
     MainAxisSize
    -0.55
    POSITIVE LOGITS
     []
    0.65
     {}
    0.58
     {'
    0.55
     {
    0.53
     AssemblyTitle
    0.51
    yaszt
    0.51
    espero
    0.51
     précie
    0.50
     datter
    0.49
     vinto
    0.49
    Activations Density 0.077%

    No Known Activations