© 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. 52246
    Prev
    Next
    INDEX
    Explanations

    words associated with the genre of punk

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

    words ending in unk

    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
    awaiter
    -0.58
    ❶
    -0.54
    SSA
    -0.54
    Boas
    -0.53
    Santis
    -0.51
    dags
    -0.49
    SAA
    -0.49
    DotNetBar
    -0.49
    DataAnnotations
    -0.48
     Autorisations
    -0.48
    POSITIVE LOGITS
     Punk
    0.97
     punk
    0.90
    Punk
    0.83
    unk
    0.82
    Funk
    0.78
     Junk
    0.76
     Funk
    0.75
    punk
    0.72
     Funky
    0.72
    UNK
    0.71
    Activations Density 0.007%

    No Known Activations