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

    Neuronpedia

    APICircuit 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. 24149
    Prev
    Next
    INDEX
    Explanations

    instances of the word "bang" and its variations in different contexts

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

    "bang" followed by proper nouns or concepts

    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
    ی
    -0.47
    NCC
    -0.42
    vii
    -0.40
    DCA
    -0.39
    CCM
    -0.38
    }{*}{
    -0.38
    şti
    -0.37
     Witherspoon
    -0.37
    Ⅲ
    -0.37
    ITV
    -0.36
    POSITIVE LOGITS
     Bang
    1.17
    Bang
    1.13
     bang
    1.09
     BANG
    1.05
    bang
    1.01
     ainfi
    0.98
     bangs
    0.91
     banging
    0.82
    BANG
    0.81
     banged
    0.81
    Activations Density 0.004%

    No Known Activations