© 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. 11-GEMMASCOPE-RES-16K
    11. 6621
    Prev
    Next
    INDEX
    Explanations

    instances of the word "once" and variations of "you" in relation to actions or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ;
    -0.51
    :
    -0.51
    ↵
    -0.48
    Skipped
    -0.46
     never
    -0.44
     henvisninger
    -0.43
    әне
    -0.43
     prévoir
    -0.43
    際
    -0.42
     as
    -0.41
    POSITIVE LOGITS
    Datuak
    1.02
     igång
    0.85
    NUMX
    0.85
     Setelah
    0.84
    ]='\
    0.83
     صوتيه
    0.80
    RenderAtEndOf
    0.80
    EndInit
    0.80
    AndEndTag
    0.78
     Após
    0.77
    Activations Density 0.257%

    No Known Activations