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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2735
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and dependencies in various contexts

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

    hypothetical or conditional statements using "if" and "you" together.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asing
    -0.34
    with
    -0.34
    piecze
    -0.34
    Zen
    -0.34
    antas
    -0.33
    enn
    -0.33
     EMP
    -0.33
    ,
    -0.33
     सुन
    -0.33
    getters
    -0.32
    POSITIVE LOGITS
    #
    0.75
    /**
    0.65
     saveiro
    0.62
     autorytatywna
    0.57
     дописавши
    0.56
    Tikang
    0.56
    transQ
    0.54
    RTHOOK
    0.53
    FieldBuilder
    0.52
    MigrationBuilder
    0.51
    Activations Density 0.223%

    No Known Activations