© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 13886
    Prev
    Next
    INDEX
    Explanations

    references to blindness and trust-related concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Trost
    -0.67
    JsonFormat
    -0.66
     Tsche
    -0.65
     Sadler
    -0.62
     FontWeight
    -0.60
     RIA
    -0.59
    brad
    -0.57
     vær
    -0.57
    ecture
    -0.57
    dtypes
    -0.56
    POSITIVE LOGITS
    blind
    1.77
     Blind
    1.76
    Blind
    1.75
     blind
    1.71
     blindness
    1.29
     blinds
    1.19
     Blinds
    1.19
     blin
    1.12
     blinded
    1.09
    盲
    1.08
    Activations Density 0.183%

    No Known Activations