© 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. 33-GEMMASCOPE-RES-16K
    11. 5112
    Prev
    Next
    INDEX
    Explanations

    code-related functions that handle data retrieval and manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.47
    enterOuterAlt
    -0.43
    basicConfig
    -0.42
    Diwedd
    -0.42
    PostConstruct
    -0.41
    InsertCommand
    -0.39
    VIAF
    -0.38
     epis
    -0.37
     UserController
    -0.36
    igure
    -0.36
    POSITIVE LOGITS
    FieldOffsetTable
    0.64
     getString
    0.51
    getInt
    0.50
    getString
    0.47
     umana
    0.46
     fieldNum
    0.45
    getBoolean
    0.44
     consigo
    0.43
    URLException
    0.43
    ötzlich
    0.43
    Activations Density 0.242%

    No Known Activations