© 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-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 14681
    Prev
    Next
    INDEX
    Explanations

    references to holes and openings in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 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
     Bioaccumulative
    -0.63
    новништво
    -0.58
     Administrativna
    -0.57
    mybatisplus
    -0.56
    stylers
    -0.56
     للمعارف
    -0.56
    +#+#
    -0.55
     marinho
    -0.53
    AndroidJUnit
    -0.52
     محفوظة
    -0.52
    POSITIVE LOGITS
     hole
    0.89
     holes
    0.87
     openings
    0.80
     open
    0.79
     opening
    0.79
     Hole
    0.75
    holes
    0.74
    Hole
    0.73
    hole
    0.73
     gaping
    0.72
    Activations Density 0.609%

    No Known Activations