© 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. 7794
    Prev
    Next
    INDEX
    Explanations

    mentions of cultural references, societal issues, and elements of belief systems

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

    followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    screwed, fucked, cussed

    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
     beschik
    -0.67
     anſ
    -0.65
     raiſ
    -0.65
     ſtate
    -0.65
     houſe
    -0.62
     fevere
    -0.62
    ſelf
    -0.61
     himſelf
    -0.61
     poffe
    -0.60
     ſever
    -0.59
    POSITIVE LOGITS
     sneaking
    1.35
     sneak
    1.31
     sne
    1.15
     crept
    1.15
     slipped
    1.13
     creeping
    1.12
     mixed
    1.09
     inserted
    1.09
     sprinkled
    1.08
    sneak
    1.04
    Activations Density 0.391%

    No Known Activations