© 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. 10877
    Prev
    Next
    INDEX
    Explanations

    references to characters and their actions in narratives

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

    following verbs like "iting", "using", "driving", or "taking."

    np_acts-logits-general · gemini-2.0-flash

    taking or continuing possession

    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
    LookAnd
    -0.57
    省市镇
    -0.50
    styleType
    -0.49
    ⤹
    -0.46
    TypedDataSet
    -0.45
    Попис
    -0.44
    autogui
    -0.40
    OCCURRED
    -0.40
    habitants
    -0.39
    AutoScale
    -0.39
    POSITIVE LOGITS
     borrowed
    0.60
     inherited
    0.59
     pening
    0.46
    setcounter
    0.45
    别人的
    0.44
     fremden
    0.43
    inherited
    0.41
    Inherited
    0.41
    arraycopy
    0.40
    borrow
    0.40
    Activations Density 0.570%

    No Known Activations