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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 10069
    Prev
    Next
    INDEX
    Explanations

    references to societal issues and regulations related to substance use, particularly tobacco and drugs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ArgsConstructor
    -0.69
     pinulongan
    -0.59
    وأضاف
    -0.57
    UnsafeEnabled
    -0.57
    Jeografia
    -0.53
    UnusedPrivate
    -0.53
    berdayakan
    -0.53
     للاسماء
    -0.49
    Comfort
    -0.49
    PointerException
    -0.49
    POSITIVE LOGITS
     restraint
    1.00
     abstinence
    0.96
     restrained
    0.91
     restrain
    0.83
     abstain
    0.83
     restrict
    0.82
     sober
    0.81
     restrictive
    0.81
     abstin
    0.81
     restricting
    0.81
    Activations Density 0.519%

    No Known Activations