© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 128549
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "spec" and its variations related to specifications or specifications in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    specifications in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Życiorys
    -0.54
     Италијани
    -0.51
     Comprometido
    -0.44
     Italijanski
    -0.42
    dropout
    -0.41
    Estar
    -0.41
     Савезне
    -0.41
     computerized
    -0.41
    Marie
    -0.40
     mad
    -0.40
    POSITIVE LOGITS
    spec
    3.03
     spec
    2.19
    SPEC
    2.09
     Spec
    1.88
     SPEC
    1.86
    Spec
    1.77
     espec
    1.38
     spéc
    1.30
     specs
    1.28
    specs
    1.24
    Activations Density 0.002%

    No Known Activations