Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 2347
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts and functions

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

    Likely misspelled or partial words

    np_acts-logits-general · gemini-2.0-flash

    Spanish/Italian/Portuguese word endings

    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
    rungsseite
    -0.81
    UVWXYZ
    -0.76
    ACIONAL
    -0.69
    ViewFeatures
    -0.67
     AssemblyCulture
    -0.66
    }{*}{}
    -0.66
    encils
    -0.66
    izante
    -0.64
    Chham
    -0.64
     nakalista
    -0.64
    POSITIVE LOGITS
     }}}
    0.40
     teatr
    0.37
     territor
    0.36
     Jednak
    0.35
    ofire
    0.35
    Baik
    0.35
     obé
    0.35
    locales
    0.34
    correre
    0.34
     estratég
    0.34
    Activations Density 0.016%

    No Known Activations