© 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. 11144
    Prev
    Next
    INDEX
    Explanations

    programming constructs such as structures, interfaces, and function definitions in coding contexts

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

    Code or mathematical notation

    np_acts-logits-general · gemini-2.0-flash

    mathematical and programming constructs

    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
    IsMutable
    -0.60
    󠁴
    -0.54
    intios
    -0.51
    FunctionFlags
    -0.50
    脚注の使い方
    -0.46
    elemField
    -0.45
    __':
    -0.45
    CROSSTALK
    -0.45
    [];
    -0.44
    __":
    -0.44
    POSITIVE LOGITS
     overall
    0.59
     Overall
    0.50
    Geplaatst
    0.46
    整體
    0.43
    Overall
    0.42
    overall
    0.41
     keseluruhan
    0.41
    itinéraire
    0.40
     Cover
    0.39
     cover
    0.39
    Activations Density 1.535%

    No Known Activations