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-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 7967
    Prev
    Next
    INDEX
    Explanations

    descriptions of impulsive or reckless behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    XmlAccessType
    -0.65
    ंदीखरीदारी
    -0.55
    ddot
    -0.55
    vespa
    -0.52
    ecutable
    -0.51
    setContentView
    -0.50
    liothèque
    -0.50
    tovers
    -0.50
     virke
    -0.50
     unanimously
    -0.49
    POSITIVE LOGITS
     drugs
    0.94
     irresponsible
    0.82
     drinking
    0.80
    Drugs
    0.79
     drug
    0.79
    drugs
    0.78
     Drugs
    0.76
     alcohol
    0.76
     partying
    0.73
     substance
    0.73
    Activations Density 0.459%

    No Known Activations