© 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. 7-GEMMASCOPE-RES-16K
    6. 8487
    Prev
    Next
    INDEX
    Explanations

    elements related to minimum values or constraints in data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.83
    gri
    -0.72
     Ballard
    -0.68
     portuguesa
    -0.67
     financière
    -0.66
     تضيفلها
    -0.66
     Smack
    -0.65
    reactstrap
    -0.64
     Jwt
    -0.63
    LinkId
    -0.63
    POSITIVE LOGITS
     MIN
    1.52
     Min
    1.49
    Min
    1.45
     min
    1.45
    MIN
    1.43
    min
    1.37
    getMin
    1.29
     getMin
    1.27
    setMin
    1.22
     MINIMUM
    1.21
    Activations Density 0.115%

    No Known Activations