© 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. 7893
    Prev
    Next
    INDEX
    Explanations

    control flow statements and error handling in a programming context

    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
    AccessorTable
    -0.55
    DeleteBehavior
    -0.44
    @[+][
    -0.41
     linkovi
    -0.41
     newBuilder
    -0.40
     EClass
    -0.37
    hoeddwyd
    -0.36
     accent
    -0.36
     Catawiki
    -0.35
    يكب
    -0.35
    POSITIVE LOGITS
    LAB
    0.54
    MigrationBuilder
    0.50
    .*")]
    0.50
    tvguidetime
    0.46
    -------------</
    0.45
    LABEL
    0.44
     fail
    0.43
     LAB
    0.43
    fail
    0.42
     LABEL
    0.42
    Activations Density 0.278%

    No Known Activations