© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 41877
    Prev
    Next
    INDEX
    Explanations

    programming-related data structures and types

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

    data types: string, array, int

    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
    expandindo
    -1.01
    +#+#
    -0.94
    UserScript
    -0.92
     queſta
    -0.90
     ſei
    -0.90
    niſſe
    -0.89
     zwiſchen
    -0.89
    uxxxx
    -0.88
    AddTagHelper
    -0.88
    ſehen
    -0.87
    POSITIVE LOGITS
    .
    0.41
    :
    0.39
    ?
    0.38
    ,
    0.37
    </strong>
    0.31
     saisir
    0.30
    S
    0.30
    ,
    0.30
    O
    0.30
    int
    0.30
    Activations Density 0.004%

    No Known Activations