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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11180
    Prev
    Next
    INDEX
    Explanations

    URLs and references to academic proceedings and conferences

    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
    valbard
    -0.42
     exposures
    -0.41
    findpost
    -0.41
     الحره
    -0.41
    لينكات
    -0.41
    supra
    -0.41
    naked
    -0.40
    AddHtmlAttribute
    -0.38
    MEP
    -0.38
     Ucraina
    -0.37
    POSITIVE LOGITS
     ACM
    0.70
    ACM
    0.63
     Computer
    0.63
    Computer
    0.60
     surla
    0.57
     computer
    0.53
     COMPUTER
    0.51
    Organisateur
    0.50
    Ubic
    0.50
     المعيارى
    0.49
    Activations Density 0.516%

    No Known Activations