© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 7739
    Prev
    Next
    INDEX
    Explanations

    references to cited figures or sections in the text

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

    figures, sections, and tables

    np_acts-logits-general · gemini-2.0-flash

    referencing figures and sections

    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
     GoogleFonts
    -0.54
    EndContext
    -0.51
    ########.
    -0.50
    UnusedPrivate
    -0.49
    RegressionTest
    -0.49
    uzz
    -0.46
    EndGlobal
    -0.44
     Monfieur
    -0.44
    stdafx
    -0.43
    KommentareTeilen
    -0.42
    POSITIVE LOGITS
    See
    1.57
     See
    1.53
    see
    1.46
     see
    1.33
     Siehe
    1.20
     siehe
    1.14
    SEE
    1.04
    siehe
    1.03
     SEE
    1.02
    Siehe
    0.99
    Activations Density 0.471%

    No Known Activations