© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4663
    Prev
    Next
    INDEX
    Explanations

    references to policies and decision-making in various contexts

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

    following "policy"

    np_acts-logits-general · gemini-2.0-flash

    policy makers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    -0.69
    تقاوى
    -0.66
    Демографія
    -0.61
     trö
    -0.51
    ]--;
    -0.51
     متعلقه
    -0.49
    ness
    -0.49
    toyage
    -0.47
     AllMovie
    -0.47
    schild
    -0.47
    POSITIVE LOGITS
    maker
    1.05
     makers
    1.00
    making
    0.98
    makers
    0.89
     maker
    0.78
    Maker
    0.72
    MAKING
    0.71
     decisions
    0.69
     formulation
    0.67
    holders
    0.67
    Activations Density 0.066%

    No Known Activations