© 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. 2-GEMMASCOPE-RES-16K
    11. 15584
    Prev
    Next
    INDEX
    Explanations

    sections of code documentation or comments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ‍♀️
    -0.64
     }}$}
    -0.61
    ‍♂️
    -0.60
    Externé
    -0.57
     }}=
    -0.56
    }-*/;
    -0.55
     ️
    -0.54
    #+#
    -0.53
     }=
    -0.53
    ſelf
    -0.52
    POSITIVE LOGITS
    <sup>
    2.88
     ${
    1.45
     $^{
    1.45
    <sub>
    1.43
     $^{\
    1.21
    /**
    1.13
    ${
    1.13
    $^{
    1.05
    /**
    1.02
     ^
    0.98
    Activations Density 0.258%

    No Known Activations