© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 10624
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and concepts related to antibody types and immunological assays

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.75
    ClientRect
    -0.71
    Personendaten
    -0.68
    
    -0.68
     pleaſure
    -0.67
    contentLoaded
    -0.66
     houſe
    -0.66
    IntoConstraints
    -0.65
     للاسماء
    -0.65
     ſich
    -0.63
    POSITIVE LOGITS
     tenue
    0.31
     -
    0.31
    ci
    0.31
    想必
    0.30
    少ない
    0.30
    Референце
    0.30
    IEF
    0.30
    ic
    0.29
    ↵↵
    0.29
    小さい
    0.29
    Activations Density 0.787%

    No Known Activations