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-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 7042
    Prev
    Next
    INDEX
    Explanations

    instances of the word "hang" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ResponseWriter
    -0.62
     miljoner
    -0.59
    MigrationBuilder
    -0.54
    __':
    
    -0.54
    ⓘ
    -0.53
    shire
    -0.53
    PreExecute
    -0.53
     metų
    -0.53
     ahogy
    -0.52
    )}_{
    -0.51
    POSITIVE LOGITS
     hang
    4.63
     hanging
    3.97
     hangs
    3.96
     HANG
    3.90
     Hang
    3.90
    Hang
    3.76
     hung
    3.75
    hang
    3.64
     Hanging
    3.53
    Hanging
    3.49
    Activations Density 0.061%

    No Known Activations