© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 3577
    Prev
    Next
    INDEX
    Explanations

    conversational cues and dialogue markers in text

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

    dialogue and conversational speech, particularly exclamatory or emotionally expressive utterances.

    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
    なるほど
    -0.46
     Wicidata
    -0.45
    Hmmmm
    -0.43
     endnu
    -0.43
     svært
    -0.43
     محفوظة
    -0.43
     verbonden
    -0.42
     rigtig
    -0.42
     strøm
    -0.42
    :✨
    -0.42
    POSITIVE LOGITS
     anyways
    0.65
    GEBURTSDATUM
    0.57
    Anyways
    0.55
     يتيمه
    0.53
     Anyways
    0.52
     wanna
    0.52
    wanna
    0.51
     espel
    0.47
    yeah
    0.47
     anyway
    0.47
    Activations Density 0.164%

    No Known Activations