© 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. 18-GEMMASCOPE-RES-16K
    11. 3915
    Prev
    Next
    INDEX
    Explanations

    expressions related to personal struggle and societal critiques

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

    Followed by words indicating time periods or differences

    np_acts-logits-general · gemini-2.0-flash

    specific instances or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.98
     '\\;'
    -0.90
    expandindo
    -0.89
     ویکی‌پدیا
    -0.84
    AndEndTag
    -0.83
    Hentet
    -0.83
    principalTable
    -0.82
    ագրություններ
    -0.80
    ValueStyle
    -0.80
    Personensuche
    -0.80
    POSITIVE LOGITS
     approach
    0.75
     option
    0.66
     technique
    0.65
     aspect
    0.63
     type
    0.62
     nature
    0.60
     column
    0.59
     situation
    0.59
     notion
    0.58
     method
    0.58
    Activations Density 1.814%

    No Known Activations