© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14321
    Prev
    Next
    INDEX
    Explanations

    aspects of programming or software development related to structured code or object-oriented elements

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

    Code snippets and imports

    np_acts-logits-general · gemini-2.0-flash

    code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    posedge
    -0.65
    TypedDataSet
    -0.63
    featureID
    -0.59
     ujednoznacz
    -0.59
    parsedMessage
    -0.58
    addCriterion
    -0.57
     onOptions
    -0.57
     himo
    -0.57
    stylers
    -0.56
    ++]=
    -0.54
    POSITIVE LOGITS
    ↵↵
    0.65
     the
    0.44
    ↵↵↵
    0.42
     Moreover
    0.41
     improvements
    0.41
    hline
    0.40
    section
    0.40
    ↵↵↵↵
    0.40
    ,
    0.39
     intptr
    0.39
    Activations Density 0.066%

    No Known Activations