© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 9849
    Prev
    Next
    INDEX
    Explanations

    symbols and terminology related to mathematical definitions and notations

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

    TeX notation within math expressions

    np_acts-logits-general · gemini-2.0-flash

    closing brace then markup

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Clara
    -0.47
     Clara
    -0.43
     Дата
    -0.42
    Ida
    -0.42
     Babu
    -0.42
    </tr>
    -0.42
     Genoa
    -0.41
     Eugen
    -0.41
    iT
    -0.41
     Ε
    -0.41
    POSITIVE LOGITS
     bershka
    0.64
     Slovenian
    0.63
    InjectMocks
    0.59
     disambiguazione
    0.57
    Garantía
    0.56
    gonic
    0.56
     Coyle
    0.56
    neurial
    0.56
    vierno
    0.55
     Mantra
    0.55
    Activations Density 2.350%

    No Known Activations