© 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. 27-GEMMASCOPE-RES-16K
    11. 6538
    Prev
    Next
    INDEX
    Explanations

    statements regarding the necessity or validity of claims

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     informée
    -0.75
     utafitiHapana
    -0.64
    #+#
    -0.62
    LookAnd
    -0.61
    aarrggbb
    -0.61
     sappiamo
    -0.60
     obviously
    -0.60
     defaultstate
    -0.57
    obviously
    -0.57
     Obviously
    -0.57
    POSITIVE LOGITS
     actually
    0.54
     indeed
    0.51
     inderdaad
    0.47
     وأن
    0.45
     ACTUALLY
    0.44
    actually
    0.42
     somehow
    0.40
    indeed
    0.39
     faktiskt
    0.39
     justru
    0.37
    Activations Density 0.700%

    No Known Activations