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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6817
    Prev
    Next
    INDEX
    Explanations

    specific character sequences or symbols in the text

    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
     z
    -0.56
     na
    -0.54
     po
    -0.53
     sk
    -0.51
     o
    -0.49
     ne
    -0.48
     kon
    -0.48
     do
    -0.47
     se
    -0.47
     li
    -0.47
    POSITIVE LOGITS
     miniaturka
    1.25
     feroit
    1.20
     Komunikasi
    1.12
     Económica
    1.11
     chrétien
    1.10
    étoit
    1.07
     pouvoit
    1.06
     Keuangan
    1.05
     Lingkungan
    1.05
     enfans
    1.04
    Activations Density 0.001%

    No Known Activations