© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 3775
    Prev
    Next
    INDEX
    Explanations

    occurrences of uncertainties and future possibilities

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

    "...not ... yet" pattern

    np_acts-logits-general · gemini-2.0-flash

    not yet

    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
    enação
    -0.53
    ATORY
    -0.48
    steamcommunity
    -0.47
    bhan
    -0.47
     originais
    -0.47
    ğunu
    -0.46
     ادامه
    -0.46
    elif
    -0.46
    thold
    -0.45
    گاب
    -0.45
    POSITIVE LOGITS
     yet
    4.49
    yet
    3.75
     Yet
    3.43
    Yet
    3.39
     YET
    3.04
     endnu
    2.25
     ännu
    2.12
     aún
    1.76
     jeszcze
    1.74
     todavía
    1.61
    Activations Density 0.426%

    No Known Activations