© 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. 30-GEMMASCOPE-RES-16K
    11. 8442
    Prev
    Next
    INDEX
    Explanations

    keywords related to legal and procedural issues

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

    about topics or subjects

    np_acts-logits-general · gemini-2.0-flash

    matters of relevance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    armed
    -0.38
    __':
    -0.37
    SuppressLint
    -0.36
    ◎
    -0.32
     Процитовано
    -0.31
    usepackage
    -0.31
    RegressionTest
    -0.31
     EClass
    -0.31
    recyclerview
    -0.31
    #+#
    -0.31
    POSITIVE LOGITS
     related
    2.30
     relating
    2.05
     pertaining
    1.88
    related
    1.83
     relacionado
    1.73
     Related
    1.73
     associated
    1.70
     związane
    1.66
     RELATED
    1.62
    Related
    1.61
    Activations Density 1.622%

    No Known Activations