© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16016
    Prev
    Next
    INDEX
    Explanations

    dates, events, and organizational details

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

    Months of the year

    np_acts-logits-general · gemini-2.0-flash

    months after dates

    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
    offsetof
    -0.53
     AssemblyTitle
    -0.50
    jooq
    -0.47
    yarnpkg
    -0.46
    InjectAttribute
    -0.45
    Vidite
    -0.44
     makeStyles
    -0.43
    oznam
    -0.42
    Ҭ
    -0.42
    ürme
    -0.41
    POSITIVE LOGITS
     October
    3.17
     September
    3.16
     April
    3.15
     July
    3.15
     June
    3.12
     February
    3.11
     November
    3.09
     December
    3.07
     January
    3.06
     March
    3.06
    Activations Density 1.410%

    No Known Activations