© 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. 10153
    Prev
    Next
    INDEX
    Explanations

    terms related to health risks and their potential consequences

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

    Negative consequences or preventative measures

    np_acts-logits-general · gemini-2.0-flash

    negative outcomes of actions

    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
    <bos>
    -0.78
    
    -0.73
     Paglinawan
    -0.68
    Autoritní
    -0.67
     autorytatywna
    -0.61
    Rohy
    -0.61
     tampaknya
    -0.58
     AspNetCore
    -0.57
    Personensuche
    -0.56
    fjspx
    -0.55
    POSITIVE LOGITS
     increased
    0.95
     serious
    0.92
     costly
    0.85
     significant
    0.81
     decreased
    0.81
    increased
    0.77
     unnecessary
    0.76
     Increased
    0.74
     problems
    0.73
     complications
    0.72
    Activations Density 0.643%

    No Known Activations