© 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. 3561
    Prev
    Next
    INDEX
    Explanations

    expressions related to causation or causes of various events and problems

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

    "cause" or its variations

    np_acts-logits-general · gemini-2.0-flash

    cause and induce

    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
    ########.
    -0.55
    ionView
    -0.49
    endregion
    -0.47
    byter
    -0.43
     Westminster
    -0.42
    tenberg
    -0.41
    hline
    -0.41
    Referanser
    -0.40
    anyahu
    -0.40
     AssemblyVersion
    -0.40
    POSITIVE LOGITS
     Cause
    1.05
     caused
    1.05
     CAUSE
    1.03
     cause
    1.01
     Caused
    0.98
    caused
    0.97
     causes
    0.97
     Causes
    0.96
     causing
    0.96
    causes
    0.95
    Activations Density 0.167%

    No Known Activations