© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 833
    Prev
    Next
    INDEX
    Explanations

    programming terminology and constructs related to classes and methods

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

    `set` and tokens that follow it

    np_acts-logits-general · gemini-2.0-flash

    setter methods

    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
    ########.
    -0.66
     intptr
    -0.64
    PerformLayout
    -0.59
    expandindo
    -0.59
     referrerpolicy
    -0.56
     kasarigan
    -0.55
    Tikang
    -0.54
    +:+
    -0.54
     ✭✭
    -0.54
    ロウィン
    -0.53
    POSITIVE LOGITS
    AfterClass
    0.47
     perdon
    0.36
    enteuer
    0.34
    缘
    0.32
    XmlAccessType
    0.32
    setScene
    0.32
    orale
    0.32
    memberof
    0.31
    iad
    0.31
    ローラー
    0.31
    Activations Density 0.047%

    No Known Activations