© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 14482
    Prev
    Next
    INDEX
    Explanations

    terms related to constraints in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sherlock
    -0.83
    ERICK
    -0.81
    Rhin
    -0.77
    +#+
    -0.73
     Blackwood
    -0.72
     tilf
    -0.70
    yargs
    -0.70
    cutta
    -0.69
    Officers
    -0.69
    BoxShadow
    -0.69
    POSITIVE LOGITS
    MyApp
    0.77
    ivore
    0.76
    }^\
    0.74
    Voir
    0.71
    Meme
    0.70
    cotch
    0.70
    RAINT
    0.70
     yall
    0.70
     broder
    0.69
    chill
    0.69
    Activations Density 0.902%

    No Known Activations