© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 16345
    Prev
    Next
    INDEX
    Explanations

    expressions indicating user intent or actions

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

    following "if you are" or "if you're"

    np_acts-logits-general · gemini-2.0-flash

    if you are

    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
     probably
    -0.81
    probably
    -0.81
     Probably
    -0.77
    Probably
    -0.76
    almost
    -0.75
    Almost
    -0.70
     rất
    -0.68
     almost
    -0.66
     probabilmente
    -0.65
    Casi
    -0.64
    POSITIVE LOGITS
     quelconque
    1.00
     any
    0.96
     anything
    0.92
     yoksa
    0.89
    有任何
    0.87
     slightest
    0.85
     jemals
    0.85
     sufficiently
    0.83
     truly
    0.83
    ใด
    0.82
    Activations Density 0.464%

    No Known Activations