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

    Neuronpedia

    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. 10858
    Prev
    Next
    INDEX
    Explanations

    references to a character named Harry in various contexts

    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
     ModelExpression
    -0.63
    Rohy
    -0.60
    
    -0.55
     vPvB
    -0.53
     protoimpl
    -0.52
     AssemblyVersion
    -0.52
     ویکی‌پدیای
    -0.52
     AspNetCore
    -0.52
     оригіналу
    -0.51
     referrerpolicy
    -0.51
    POSITIVE LOGITS
     Potter
    0.70
     Harry
    0.68
    Harry
    0.65
    Potter
    0.64
     harry
    0.56
     potter
    0.55
     HARRY
    0.53
     POT
    0.52
    harry
    0.46
    HARRY
    0.46
    Activations Density 0.171%

    No Known Activations