© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 35-GEMMASCOPE-RES-16K
    11. 12092
    Prev
    Next
    INDEX
    Explanations

    references to formal documents or structured reports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.40
    出版年
    -0.39
    󠁳
    -0.33
     indisponible
    -0.30
    izophren
    -0.29
    ennia
    -0.27
    tifkan
    -0.26
    ầy
    -0.25
    krank
    -0.25
    InputTagHelper
    -0.24
    POSITIVE LOGITS
     ending
    2.88
     Ending
    2.41
     ended
    2.39
     finishing
    2.31
     finish
    2.31
     endings
    2.25
     ends
    2.25
     finishes
    2.23
    Ending
    2.23
     concluding
    2.06
    Activations Density 1.430%

    No Known Activations