© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11367
    Prev
    Next
    INDEX
    Explanations

    constructs related to programming functions and methods

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

    Code definitions or declarations

    np_acts-logits-general · gemini-2.0-flash

    key-value pairs, JSON

    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
    TagMode
    -0.56
     ſtand
    -0.41
     ⓒ
    -0.40
    setViewportView
    -0.36
     Efq
    -0.35
     ſtate
    -0.34
     strdup
    -0.34
     beſt
    -0.34
     évi
    -0.34
     TextAlign
    -0.34
    POSITIVE LOGITS
     juzgar
    0.53
     particulars
    0.52
    oggetto
    0.51
    agisse
    0.50
     Übernach
    0.50
    SharedCtor
    0.50
    httphttps
    0.50
     patrulla
    0.49
     Particulars
    0.49
    identité
    0.49
    Activations Density 0.417%

    No Known Activations