Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 3352
    Prev
    Next
    INDEX
    Explanations

    themes related to evasion or escape from threats or danger

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

    Avoiding negative consequences

    np_acts-logits-general · gemini-2.0-flash

    escape or encounter danger

    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
    AlterField
    -0.66
     StatefulWidget
    -0.58
    Datuak
    -0.58
     nahilalakip
    -0.58
    Espèce
    -0.55
    ChromeDriver
    -0.54
     prisonniers
    -0.54
    enumii
    -0.52
    TagMode
    -0.50
    onOptions
    -0.50
    POSITIVE LOGITS
     scrutiny
    1.15
     onslaught
    0.86
     criticism
    0.85
     attacks
    0.83
     backlash
    0.79
     pressures
    0.79
     wrath
    0.77
     fate
    0.77
     ridicule
    0.77
     relentless
    0.75
    Activations Density 0.476%

    No Known Activations