© 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 EvalsExportsinterp-engineNEWAPI 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. 8035
    Prev
    Next
    INDEX
    Explanations

    concepts related to legal terms and frameworks

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

    before/after parenthetical punctuation

    np_acts-logits-general · gemini-2.0-flash

    legal, technical, and scientific contexts

    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
     however
    -0.64
     linkovi
    -0.60
     certainly
    -0.59
     betweenstory
    -0.58
     obviously
    -0.58
    tonode
    -0.56
     ModelExpression
    -0.56
     nakalista
    -0.56
    WriteTagHelper
    -0.56
    GOTREF
    -0.55
    POSITIVE LOGITS
    ตัวเอง
    0.40
    Revenir
    0.35
     وأن
    0.33
    ἶ
    0.32
     ""))
    0.31
     שלה
    0.30
     ferait
    0.30
    //
    0.29
     lenne
    0.29
     would
    0.28
    Activations Density 1.415%

    No Known Activations