© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 9413
    Prev
    Next
    INDEX
    Explanations

    programming constructs and operations that involve data structures and method calls

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Audiodateien
    -0.61
     erste
    -0.56
     first
    -0.54
     myſelf
    -0.50
    第一
    -0.50
     ersten
    -0.50
    的第一
    -0.50
    first
    -0.50
    FirstOrDefault
    -0.49
    第一个
    -0.48
    POSITIVE LOGITS
     AttributeSet
    0.43
     findAll
    0.41
     getAll
    0.40
    üttel
    0.40
    tissage
    0.40
    レギュラー
    0.38
    isContained
    0.38
    nasium
    0.37
    getAll
    0.37
    ditos
    0.37
    Activations Density 0.231%

    No Known Activations