© 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. 21-GEMMASCOPE-RES-16K
    11. 12848
    Prev
    Next
    INDEX
    Explanations

    definitions, descriptions, or mentions related to nationality and citizenship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.69
     Periodicals
    -0.56
     Púb
    -0.53
    MENAFN
    -0.53
     Adults
    -0.52
     giornal
    -0.52
     persoane
    -0.52
     esterni
    -0.51
    Semantics
    -0.51
    dekat
    -0.51
    POSITIVE LOGITS
     Canadian
    1.66
     Australian
    1.58
     American
    1.56
     Japanese
    1.52
     Italian
    1.51
     British
    1.49
     German
    1.49
     Israeli
    1.44
     Mexican
    1.42
     Irish
    1.41
    Activations Density 1.072%

    No Known Activations