Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 64627
    Prev
    Next
    INDEX
    Explanations

    phrases and terminology associated with scoring or ratings

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

    score on

    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
     Jan
    -0.58
     (
    -0.54
     new
    -0.51
     It
    -0.51
     J
    -0.51
     Van
    -0.50
     Mat
    -0.50
     V
    -0.49
     Jimenez
    -0.49
     Al
    -0.49
    POSITIVE LOGITS
     score
    1.16
    score
    1.12
     Score
    1.11
    Score
    1.05
     SCORE
    0.98
    getScore
    0.96
    SCORE
    0.93
     Scores
    0.87
     pleaſure
    0.84
     scores
    0.83
    Activations Density 0.016%

    No Known Activations