© 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. 31-GEMMASCOPE-RES-16K
    11. 2690
    Prev
    Next
    INDEX
    Explanations

    instances of speaking and communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "speak" or its variants in contexts of communication and expression.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ง
    -0.34
    esterno
    -0.33
    tor
    -0.33
     Ausnahme
    -0.32
     roj
    -0.32
    SUMMARY
    -0.31
     basah
    -0.31
    กว่า
    -0.31
    seitig
    -0.31
    affaire
    -0.31
    POSITIVE LOGITS
     spoke
    0.70
     spoken
    0.67
     speaks
    0.67
     speak
    0.66
     Spoken
    0.64
     Speaks
    0.64
     Speak
    0.62
    Hentet
    0.61
     fluent
    0.59
     CURIAM
    0.59
    Activations Density 0.077%

    No Known Activations