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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 8595
    Prev
    Next
    INDEX
    Explanations

    references to statistical methodologies and findings in scientific literature

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

    Punctuations such as periods and commas

    np_acts-logits-general · gemini-2.0-flash

    journal titles and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.66
    ########.
    -0.52
    ünstler
    -0.49
    RequiresApi
    -0.49
    licz
    -0.45
    例文
    -0.45
     pec
    -0.43
     Genomic
    -0.43
     FontWeight
    -0.42
    stateProvider
    -0.42
    POSITIVE LOGITS
     Journal
    1.05
    Journal
    0.88
     JOURNAL
    0.81
     journal
    0.81
     J
    0.76
    MigrationBuilder
    0.73
    llery
    0.66
    SequentialGroup
    0.66
     rivista
    0.65
    ournal
    0.65
    Activations Density 0.770%

    No Known Activations