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

    Neuronpedia

    Jacobian LensNEW
    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. 15-GEMMASCOPE-RES-16K
    11. 2935
    Prev
    Next
    INDEX
    Explanations

    sequences of numerical data and their relevance in scientific writing

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

    numbers, particularly in numerical and reference formats related to citations or statistical data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seitz
    -0.58
    MigrationBuilder
    -0.56
    TagMode
    -0.55
    iſt
    -0.54
    bonucleic
    -0.54
    flich
    -0.54
    orini
    -0.53
    ɾ
    -0.52
    dingen
    -0.52
     äta
    -0.52
    POSITIVE LOGITS
    enterOuterAlt
    0.63
    XmlIgnore
    0.52
    تقاوى
    0.52
    OGND
    0.49
     оригіналу
    0.47
    matchCondition
    0.47
     raad
    0.47
    autorest
    0.47
    JsonPropertyName
    0.44
    vertissement
    0.44
    Activations Density 0.270%

    No Known Activations