© 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. 18-GEMMASCOPE-RES-16K
    11. 15285
    Prev
    Next
    INDEX
    Explanations

    data classification and specific codes or identifiers related to datasets or experiments

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

    References or citations

    np_acts-logits-general · gemini-2.0-flash

    4D, 3D, CA following numbers

    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
    ConstraintMaker
    -0.72
    ErrUnexpectedEOF
    -0.71
     FontWeight
    -0.70
     चीज़ों
    -0.70
    DoubleQuotes
    -0.70
    citenamefont
    -0.69
     ProtoMessage
    -0.68
     بيها
    -0.66
    InstrumentedTest
    -0.66
    ]")]
    -0.64
    POSITIVE LOGITS
    Kaynakça
    0.70
    usermodel
    0.60
    internalType
    0.48
    Xna
    0.46
    Przypisy
    0.45
     ESO
    0.42
    Virt
    0.41
     OMITBAD
    0.40
    kenal
    0.39
    既
    0.39
    Activations Density 1.198%

    No Known Activations