© 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. 28-GEMMASCOPE-RES-16K
    11. 10452
    Prev
    Next
    INDEX
    Explanations

    terms related to variability and statistical factors affecting health outcomes

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

    Followed by lists or explanations

    np_acts-logits-general · gemini-2.0-flash

    including examples

    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
    sizeCache
    -0.42
    cal
    -0.40
    자가
    -0.36
    aarrggbb
    -0.34
    kal
    -0.34
    Nun
    -0.33
    igera
    -0.33
    AutoScaleMode
    -0.33
     الحره
    -0.32
    clase
    -0.31
    POSITIVE LOGITS
     including
    1.35
     antaranya
    1.23
     Including
    1.16
    Including
    1.15
    包括
    1.12
    antaranya
    1.11
     waaronder
    1.09
    including
    1.07
     INCLUDING
    1.07
     включая
    1.05
    Activations Density 0.782%

    No Known Activations