© 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
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 7335
    Prev
    Next
    INDEX
    Explanations

    formatting indicators in text

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

    Text in scientific publications before acknowledgements

    np_acts-logits-general · gemini-2.0-flash

    section labels followed by colon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </i>
    -0.55
    </h6>
    -0.52
    <i>
    -0.42
    <blockquote>
    -0.42
    <b>
    -0.41
    </u>
    -0.41
    </h5>
    -0.41
    </s>
    -0.39
    **********/
    -0.39
     badan
    -0.39
    POSITIVE LOGITS
    ValueStyle
    0.62
     noDo
    0.60
    styleType
    0.59
    afficheront
    0.57
    Hentet
    0.57
     تضيفلها
    0.55
    دانشنامهٔ
    0.54
     Italijanski
    0.54
    CppMethod
    0.53
    TEMPO
    0.53
    Activations Density 0.050%

    No Known Activations