© 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. 41011
    Prev
    Next
    INDEX
    Explanations

    references to technical terms and functions in programming or data structures

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

    mathematical notation or code

    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
    featureID
    -0.46
    Carriera
    -0.44
    quiao
    -0.42
     Aristote
    -0.41
    IDL
    -0.41
     surla
    -0.39
    IVERY
    -0.39
    EDEFAULT
    -0.39
    PickerController
    -0.38
    userdetails
    -0.38
    POSITIVE LOGITS
     disambiguazione
    0.48
     regener
    0.41
     hasattr
    0.39
     regenerated
    0.38
     compartida
    0.38
    __(/*!
    0.38
     linkovi
    0.37
     predic
    0.37
     pertenec
    0.37
     تانيه
    0.37
    Activations Density 0.245%

    No Known Activations