© 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 80535
    Prev
    Next
    INDEX
    Explanations

    punctuation and special characters used in programming syntax

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

    structurized code delimiters

    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
     “.
    -0.51
     nonatomic
    -0.48
    .•
    -0.46
    WebControls
    -0.45
     bé
    -0.44
    /**
    -0.43
    ”(
    -0.41
     conting
    -0.41
    “.
    -0.41
     som
    -0.40
    POSITIVE LOGITS
    principalTable
    0.66
    mapStateToProps
    0.57
    seamnă
    0.55
     iluminação
    0.54
     varandra
    0.54
     dumne
    0.52
     culoare
    0.52
    oarece
    0.52
     matéria
    0.52
     escalier
    0.51
    Activations Density 0.001%

    No Known Activations