© 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. 39-GEMMASCOPE-RES-16K
    11. 4111
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate presence and involvement of individuals in discussions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ioutil
    -0.37
    transQ
    -0.35
    among
    -0.35
     hyvin
    -0.33
    astify
    -0.31
    Among
    -0.30
     وس
    -0.29
    yaf
    -0.29
    acter
    -0.29
     dưới
    -0.29
    POSITIVE LOGITS
     supposed
    1.00
    supposed
    0.82
     capable
    0.71
     doing
    0.70
     suppose
    0.67
     suppos
    0.66
     purported
    0.65
     SUP
    0.64
     referring
    0.63
     saying
    0.62
    Activations Density 0.204%

    No Known Activations