© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 13151
    Prev
    Next
    INDEX
    Explanations

    specific entities and organizations, particularly names related to institutions and legal firms

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    before "Ltd", "Inc", "com", "REPORT", "Report"

    np_acts-logits-general · gemini-2.0-flash

    company names and domain suffixes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     szükség
    -0.31
    ❋
    -0.28
     însă
    -0.28
     előtt
    -0.27
     pourtant
    -0.27
     Chbosky
    -0.26
     eszköz
    -0.25
     సౌకర్య
    -0.25
     needs
    -0.25
     nevoie
    -0.24
    POSITIVE LOGITS
    SourceChecksum
    0.83
    <unused8>
    0.77
    <unused41>
    0.77
    <unused16>
    0.77
    <unused14>
    0.77
    [@BOS@]
    0.77
    <pad>
    0.77
    <unused28>
    0.76
    <unused23>
    0.76
    <unused3>
    0.76
    Activations Density 1.295%

    No Known Activations