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. 11195
    Prev
    Next
    INDEX
    Explanations

    discussions about accountability and oversight in various contexts

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

    Comes after a word indicating absence or lack

    np_acts-logits-general · gemini-2.0-flash

    lack absence omission

    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
    expandindo
    -0.70
     ISNI
    -0.63
    CloseOperation
    -0.63
    vertx
    -0.62
    }]
    
    -0.59
    istoitu
    -0.58
     MotionEvent
    -0.58
    CodedInputStream
    -0.55
    bukkit
    -0.54
    IBAction
    -0.54
    POSITIVE LOGITS
     adequately
    1.04
     adequate
    1.02
     properly
    1.01
     decent
    0.95
     proper
    0.93
    Proper
    0.88
     bothered
    0.85
     PROPER
    0.83
     meaningful
    0.83
    properly
    0.82
    Activations Density 0.592%

    No Known Activations