© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 11161
    Prev
    Next
    INDEX
    Explanations

    references to a specific character named "Cha"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Cha" or "cha" prefixes

    np_acts-logits-general · gemini-2.0-flash

    Chameleons and words starting with Cha:

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erover
    -0.67
    versiti
    -0.65
    AccessorTable
    -0.61
     Municipalidad
    -0.60
    yaf
    -0.56
     primas
    -0.54
    }\}
    -0.54
    ScopeManager
    -0.54
    throws
    -0.54
     FetchType
    -0.53
    POSITIVE LOGITS
     Cha
    0.62
     cha
    0.59
    Cha
    0.58
     Vikipedi
    0.53
    otic
    0.49
     habari
    0.47
    meleon
    0.47
     tâche
    0.46
     carattere
    0.46
     Приступљено
    0.45
    Activations Density 0.111%

    No Known Activations