© 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. 3522
    Prev
    Next
    INDEX
    Explanations

    indications of needs and requests for assistance

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

    Follows verbs like "allow," "ask," "tell"

    np_acts-logits-general · gemini-2.0-flash

    allow, ask, deny, offer, tell, help

    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
     you
    -1.52
     você
    -1.10
     contigo
    -1.09
    you
    -1.04
     شما
    -0.96
    You
    -0.92
     usted
    -0.88
     بتوان
    -0.88
     Ihnen
    -0.84
     You
    -0.84
    POSITIVE LOGITS
     yourself
    1.83
    yourself
    1.34
     Yourself
    1.31
     yourselves
    1.23
     YOURSELF
    1.22
    Yourself
    0.93
     thyself
    0.83
     your
    0.78
     jezelf
    0.76
     them
    0.76
    Activations Density 0.407%

    No Known Activations