© 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 EvalsExportsAPI 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. 14472
    Prev
    Next
    INDEX
    Explanations

    technical specifications and compatibility details related to software updates and drivers

    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
    NameInMap
    -0.43
    ioutil
    -0.39
     '../../../../
    -0.37
    twimg
    -0.36
    glLoadIdentity
    -0.35
    vident
    -0.35
     pulumi
    -0.35
     ASM
    -0.35
    quing
    -0.34
     VAS
    -0.34
    POSITIVE LOGITS
     compatibility
    2.30
     compatible
    2.23
    compatible
    1.97
     compatibles
    1.95
     Compatibility
    1.95
     compati
    1.94
     kompati
    1.94
     Compatible
    1.92
     kompatibel
    1.86
     COMPAT
    1.84
    Activations Density 0.742%

    No Known Activations