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. 20-GEMMASCOPE-RES-16K
    6. 15160
    Prev
    Next
    INDEX
    Explanations

    terms related to injury and their consequences

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

    Follows specific nouns

    np_acts-logits-general · gemini-2.0-flash

    it, pronoun usage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     OFDb
    -0.74
    aarrggbb
    -0.68
    CloseOperation
    -0.68
     Roskov
    -0.66
    )、
    -0.65
     **/
    
    -0.63
    )、
    -0.63
     */;
    -0.62
    :]:
    -0.61
     "",
    
    -0.61
    POSITIVE LOGITS
     it
    1.37
     It
    1.16
    It
    1.14
     оно
    0.86
    มัน
    0.84
    it
    0.83
     มัน
    0.82
    它
    0.80
     它
    0.77
     they
    0.67
    Activations Density 0.289%

    No Known Activations