© 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. 7558
    Prev
    Next
    INDEX
    Explanations

    concepts related to effective writing and communication

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

    Grammar, diction, and sentence construction

    np_acts-logits-general · gemini-2.0-flash

    grammar and sentence structure

    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
    Билгалдахарш
    -0.88
    AutoScale
    -0.64
    !*\
    -0.63
    addCriterion
    -0.59
    tvguidetime
    -0.59
    UNIDENTIFIED
    -0.51
    isContained
    -0.50
    webElementGuid
    -0.49
     &___
    -0.49
    baix
    -0.49
    POSITIVE LOGITS
     sentence
    0.95
     sentences
    0.94
     Sentence
    0.80
    sentence
    0.80
     Sentences
    0.80
     flow
    0.75
    Sent
    0.74
    sentences
    0.73
     gram
    0.73
     structure
    0.72
    Activations Density 0.276%

    No Known Activations