© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5120
    Prev
    Next
    INDEX
    Explanations

    words with specific prefixes or roots that suggest a relationship to healing or care

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

    Appears before or within nonsensical words

    np_acts-logits-general · gemini-2.0-flash

    following `su`, `tu`, `gu`, `nu`, `hu`, `ingu`, `aqu`

    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
    ValueStyle
    -0.72
    TRAILING
    -0.53
    ammlung
    -0.51
    FormsModule
    -0.49
    lines
    -0.46
     FormsModule
    -0.46
    sys
    -0.45
    tan
    -0.44
    cstring
    -0.44
     null
    -0.44
    POSITIVE LOGITS
    uuuu
    0.76
    uuu
    0.74
    uuuuu
    0.68
     mergeFrom
    0.55
    getInputStream
    0.53
    tilities
    0.52
    UUUU
    0.52
    o
    0.52
    u
    0.52
    uu
    0.51
    Activations Density 0.261%

    No Known Activations