© 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. 2-GEMMASCOPE-RES-16K
    11. 6249
    Prev
    Next
    INDEX
    Explanations

    the occurrence of the word "character" and its variations in the context of descriptions or discussions about various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CppMethod
    -0.75
     pseudos
    -0.51
    abestanden
    -0.51
     chi̍t
    -0.51
    oneta
    -0.51
    inSlope
    -0.50
    xodo
    -0.50
     Chinese
    -0.50
    stateMutability
    -0.50
    findpost
    -0.50
    POSITIVE LOGITS
     character
    0.63
    Character
    0.56
     Character
    0.52
     constantly
    0.52
     Савезне
    0.49
     continually
    0.48
     agreed
    0.47
     CHARACTER
    0.46
     Grecs
    0.44
    character
    0.42
    Activations Density 0.078%

    No Known Activations