© 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. 5374
    Prev
    Next
    INDEX
    Explanations

    structured legal language and terms related to governance and authority

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

    Commas followed by relative pronouns

    np_acts-logits-general · gemini-2.0-flash

    connecting clauses with which

    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
     EconPapers
    -0.71
    bootstrapcdn
    -0.65
    enumi
    -0.63
    MigrationBuilder
    -0.62
    enumii
    -0.58
    +#+#
    -0.57
     ddelweddau
    -0.57
    ambién
    -0.56
    ulongan
    -0.54
     محفوظة
    -0.54
    POSITIVE LOGITS
    core
    0.35
     whose
    0.32
    充电
    0.31
    keyColumn
    0.30
    อัน
    0.30
    pieza
    0.30
     aans
    0.30
     so
    0.29
    ----</
    0.29
     which
    0.29
    Activations Density 0.313%

    No Known Activations