© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 95789
    Prev
    Next
    INDEX
    Explanations

    terms related to paternity and legitimacy in legal contexts

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

    paternity, fidgeting, TRIB, Merritt, Plung, Hahaha, Ducommun

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -2.38
    pośred
    -0.68
    ekš
    -0.65
    vény
    -0.61
     שח
    -0.60
     الاول
    -0.59
    ział
    -0.58
    JKLM
    -0.57
    <h2>
    -0.57
    yszer
    -0.56
    POSITIVE LOGITS
    zelfde
    0.85
    ه
    0.68
    sweise
    0.68
    iyle
    0.67
    ième
    0.66
    ی
    0.66
     يتيمه
    0.65
    ený
    0.63
    enchymal
    0.63
     contextLoads
    0.62
    Activations Density 3.247%

    No Known Activations