© 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. 34-GEMMASCOPE-RES-16K
    11. 4754
    Prev
    Next
    INDEX
    Explanations

    technical and scientific terminology related to medical procedures and diagnoses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.94
     laſſen
    -0.94
     wiſſen
    -0.91
     témoig
    -0.90
    <unused28>
    -0.90
    <unused8>
    -0.90
    <unused16>
    -0.90
    <unused41>
    -0.90
    <unused3>
    -0.90
    <pad>
    -0.90
    POSITIVE LOGITS
     (
    2.72
    （
    1.53
     ("
    1.41
     (“
    1.38
    (
    1.33
     ('
    1.25
     (‘
    1.21
     («
    1.19
     ($
    1.16
     （
    1.16
    Activations Density 11.617%

    No Known Activations