© 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. 1163
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to "corruption" and "Cornel," indicating a focus on social and political critique

    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
    AsUp
    -0.76
    ########.
    -0.73
     FontWeight
    -0.69
    yntaxException
    -0.69
     SDLK
    -0.67
     Picchu
    -0.64
    uldade
    -0.61
     تكبرها
    -0.60
    ensement
    -0.59
    ★☆
    -0.58
    POSITIVE LOGITS
     COR
    0.65
     kor
    0.59
     Cornel
    0.59
    Kens
    0.57
     Kor
    0.55
     electrónicos
    0.54
     Cornelia
    0.54
    ReusableCell
    0.54
    stück
    0.54
    ztály
    0.53
    Activations Density 0.130%

    No Known Activations