© 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. 94708
    Prev
    Next
    INDEX
    Explanations

    HTML tags, particularly those associated with lists and structural elements

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

    mathematical expressions and code

    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
     queſta
    -1.63
    
    -1.56
    <unused41>
    -1.54
    [@BOS@]
    -1.53
    <unused52>
    -1.53
    <unused23>
    -1.53
    <unused43>
    -1.53
    <unused28>
    -1.53
    <unused8>
    -1.53
    <unused14>
    -1.53
    POSITIVE LOGITS
    The
    0.85
    1
    0.82
    2
    0.76
    0
    0.75
    I
    0.73
     
    0.71
    :
    0.69
    4
    0.66
     The
    0.66
    ↵↵
    0.66
    Activations Density 0.000%

    No Known Activations