Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 7659
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and expressions of uncertainty or assistance

    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
    bootstrapcdn
    -0.59
    しか
    -0.59
    RTGC
    -0.58
    RTCF
    -0.54
     ModelExpression
    -0.52
     esternos
    -0.50
     StatefulWidget
    -0.49
    ないと
    -0.49
    出版年
    -0.48
     nonUne
    -0.48
    POSITIVE LOGITS
     simply
    3.25
     just
    3.22
    simply
    2.81
     simplemente
    2.80
     просто
    2.75
     merely
    2.67
    just
    2.63
     semplicemente
    2.56
     simplesmente
    2.53
     simplement
    2.52
    Activations Density 2.445%

    No Known Activations