© 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. 10962
    Prev
    Next
    INDEX
    Explanations

    characters involved in fantasy or supernatural themes

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

    Character names or descriptions

    np_acts-logits-general · gemini-2.0-flash

    character descriptions by name or role

    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
    saraba
    -0.66
    ThroughAttribute
    -0.64
    цездатний
    -0.62
     AssemblyCulture
    -0.61
     disambiguazione
    -0.59
    में
    -0.56
    +#+#
    -0.55
     själva
    -0.55
    vedades
    -0.53
    transQ
    -0.53
    POSITIVE LOGITS
     who
    1.32
     named
    1.10
     whom
    1.01
    who
    0.83
    ess
    0.79
     manqué
    0.77
    whom
    0.76
     wearing
    0.75
     whose
    0.73
     boy
    0.70
    Activations Density 0.329%

    No Known Activations