© 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. 30-GEMMASCOPE-RES-16K
    11. 11153
    Prev
    Next
    INDEX
    Explanations

    references to time and sequencing in narratives

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

    "It was" or similar phrases indicating a delayed action

    np_acts-logits-general · gemini-2.0-flash

    first or later events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .*")]
    -0.52
    rawDesc
    -0.47
    buttonShape
    -0.44
     kasarigan
    -0.43
    fromnode
    -0.41
    Carriera
    -0.41
     BoxFit
    -0.40
    pstead
    -0.40
     alba
    -0.39
    FormTagHelper
    -0.39
    POSITIVE LOGITS
     dopiero
    1.75
     only
    1.26
     belated
    1.10
    ようやく
    1.04
     recién
    1.02
     seulement
    1.01
    Only
    1.00
     Only
    0.98
    only
    0.98
     først
    0.98
    Activations Density 0.571%

    No Known Activations