© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 13104
    Prev
    Next
    INDEX
    Explanations

    instances of affirmative language and expressions of agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AddTagHelper
    -0.57
    enumi
    -0.48
    enumii
    -0.40
    AndEndTag
    -0.40
     nakalista
    -0.40
    endphp
    -0.39
     NSCoder
    -0.39
    этому
    -0.39
     fört
    -0.39
     ब्रेकडाउन
    -0.38
    POSITIVE LOGITS
    ########.
    0.50
    AutoScale
    0.46
    bkz
    0.46
    reportWebVitals
    0.44
    coming
    0.42
    Cyfeiriadau
    0.42
     Coming
    0.41
    位
    0.41
    lighting
    0.39
    Forge
    0.39
    Activations Density 0.986%

    No Known Activations