© 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. 770
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and roles in formal proceedings

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

    Follows professions, groups, or organizations

    np_acts-logits-general · gemini-2.0-flash

    roles and actions

    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
    MigrationBuilder
    -0.65
     betweenstory
    -0.57
     ujednoznacz
    -0.55
    IUrlHelper
    -0.52
    ]")]
    -0.51
     invokingState
    -0.50
    ⤹
    -0.49
    featureID
    -0.48
     nonUne
    -0.48
     lenker
    -0.45
    POSITIVE LOGITS
    󠁢
    0.34
     because
    0.32
    mpä
    0.31
     către
    0.30
     during
    0.30
    AndEndTag
    0.29
     after
    0.29
     Weltkrieg
    0.29
     kerana
    0.29
    nativeElement
    0.29
    Activations Density 0.574%

    No Known Activations