© 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. 15205
    Prev
    Next
    INDEX
    Explanations

    conditional statements and phrases indicating prerequisites or dependencies

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

    Begins with "If" or "When"

    np_acts-logits-general · gemini-2.0-flash

    if/when conditional clauses

    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
    -0.88
    Vidite
    -0.81
    #+#
    -0.81
    opsida
    -0.74
    ValueStyle
    -0.74
     समीक्षक
    -0.74
    __":
    -0.74
     ExecuteAsync
    -0.73
    WireFormatLite
    -0.73
     canst
    -0.72
    POSITIVE LOGITS
     compared
    0.65
     so
    0.62
     if
    0.58
     So
    0.48
     dibanding
    0.48
     not
    0.47
     compare
    0.46
     houver
    0.46
     will
    0.46
     you
    0.46
    Activations Density 0.181%

    No Known Activations