© 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. 13427
    Prev
    Next
    INDEX
    Explanations

    punctuation and structural elements related to data and references

    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
    -0.68
     Surprisingly
    -0.59
     sorely
    -0.58
     complacent
    -0.56
     sabotage
    -0.56
     cruelly
    -0.55
     generously
    -0.55
     frankly
    -0.54
    Surprisingly
    -0.54
     sobbed
    -0.54
    POSITIVE LOGITS
     Wiktionnaire
    0.48
     fysis
    0.47
     zwykle
    0.47
    __":
    0.45
    astify
    0.44
     validamos
    0.43
    enderror
    0.42
    ########.
    0.41
     raiſ
    0.40
     altså
    0.40
    Activations Density 1.174%

    No Known Activations