© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 112367
    Prev
    Next
    INDEX
    Explanations

    instance method declarations in programming code

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

    `set` followed by programming types

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    NameInMap
    -0.70
    RefNanny
    -0.66
    drawSprites
    -0.47
    featureID
    -0.46
    Portale
    -0.44
     estekak
    -0.42
     jspb
    -0.42
    nezeu
    -0.41
    offsetof
    -0.41
     bArr
    -0.41
    POSITIVE LOGITS
     AssemblyCompany
    0.50
     anteriore
    0.50
    makeConstraints
    0.42
     esterna
    0.41
    Personendaten
    0.41
     sóc
    0.40
     ulub
    0.40
    replaced
    0.40
     rzecz
    0.40
     Glied
    0.40
    Activations Density 0.007%

    No Known Activations