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

    Neuronpedia

    Jacobian LensNEW
    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. 31-GEMMASCOPE-RES-16K
    11. 7229
    Prev
    Next
    INDEX
    Explanations

    elements of dialogue or speech within the text

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

    phrases where a verb conveys that something communicates or reveals information, particularly "said," "speaks," and "tell."

    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
     BoxFit
    -0.50
    ۣ
    -0.37
     متعلقه
    -0.33
     généraux
    -0.32
     useState
    -0.31
    AutoField
    -0.31
     theore
    -0.30
    </>
    -0.30
    ModelAdmin
    -0.30
    fpm
    -0.30
    POSITIVE LOGITS
     speaks
    1.47
     speak
    1.37
     Speak
    1.16
     Speaks
    1.16
    Speak
    1.14
    speak
    1.11
     speaking
    0.97
     spoke
    0.95
    speaking
    0.91
     hablan
    0.90
    Activations Density 0.226%

    No Known Activations