© 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. 8887
    Prev
    Next
    INDEX
    Explanations

    terms related to string data structures and operations

    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
     насељу
    -0.60
    expandindo
    -0.58
    Ārējās
    -0.54
    enumii
    -0.52
    inSlope
    -0.50
    󠁿
    -0.49
     متحده
    -0.48
    SaveChangesAsync
    -0.47
    millimeters
    -0.46
     виправивши
    -0.46
    POSITIVE LOGITS
     Str
    0.52
     str
    0.47
     Strö
    0.44
     Ström
    0.40
     démo
    0.39
     STR
    0.39
     confidentialité
    0.37
     Jerusalén
    0.37
     partenariat
    0.36
     personnalité
    0.36
    Activations Density 0.068%

    No Known Activations