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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1990
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific methodologies and classifications

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

    parametric completeness and entry fiction

    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
     ob
    -0.35
     
    -0.31
    ↵
    -0.31
     You
    -0.30
      
    -0.30
     I
    -0.26
     unknown
    -0.26
    ICALLY
    -0.25
    EDIA
    -0.25
     lin
    -0.25
    POSITIVE LOGITS
     betweenstory
    0.88
    𑄨
    0.76
    󰈻
    0.75
    <unused68>
    0.75
    <unused52>
    0.75
    <unused41>
    0.75
    <unused14>
    0.75
    <unused1>
    0.74
    [@BOS@]
    0.74
    <pad>
    0.74
    Activations Density 0.395%

    No Known Activations