© 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. 22-GEMMASCOPE-RES-16K
    11. 11323
    Prev
    Next
    INDEX
    Explanations

    names of political figures and their affiliations or actions

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

    elected officials

    np_acts-logits-general · gemini-2.0-flash

    political office holders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rawDesc
    -0.49
    pojo
    -0.44
    uxxxx
    -0.43
    ribadian
    -0.43
     ffilm
    -0.42
    dessous
    -0.41
    PhysRev
    -0.40
    <bos>
    -0.40
    inherits
    -0.40
     кро
    -0.39
    POSITIVE LOGITS
     congressman
    1.71
     Congressman
    1.67
     senator
    1.63
     legislator
    1.59
     lawmaker
    1.58
     congressional
    1.57
     Senator
    1.56
     legislators
    1.56
     Congressional
    1.54
     senators
    1.52
    Activations Density 0.313%

    No Known Activations