© 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-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 9892
    Prev
    Next
    INDEX
    Explanations

    conditional and hypothetical language, often indicating possibilities or requirements

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

    Conditional statements (if, once, after, following)

    np_acts-logits-general · gemini-2.0-flash

    if/then constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 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
    MLLoader
    -0.61
    thâu
    -0.54
     pinulongan
    -0.53
     GoogleFonts
    -0.52
     AssemblyCulture
    -0.51
     itſelf
    -0.50
    ẨM
    -0.49
    ympto
    -0.48
     kasarigan
    -0.47
    .”—
    -0.47
    POSITIVE LOGITS
     isso
    0.49
     this
    0.46
    之为
    0.41
    นั้น
    0.41
     hacerlo
    0.41
     they
    0.40
     resourceCulture
    0.39
     ذلك
    0.39
     ऐसा
    0.39
     ello
    0.38
    Activations Density 0.455%

    No Known Activations