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. 31-GEMMASCOPE-RES-16K
    6. 1073
    Prev
    Next
    INDEX
    Explanations

    interactions and dialogues between characters in a narrative

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

    words that express emotional intensity, hesitation, or internal conflict within narrative passages.

    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
     ourselves
    -0.52
     we
    -0.52
     “
    -0.52
     saya
    -0.49
     our
    -0.48
     (!)
    -0.48
     нам
    -0.47
     "
    -0.47
     ours
    -0.45
    saya
    -0.45
    POSITIVE LOGITS
     Infórmanos
    0.63
    ScopeManager
    0.57
     mierda
    0.57
    ญิง
    0.56
    AddTagHelper
    0.55
     CreateTagHelper
    0.54
     idiota
    0.52
    niosek
    0.50
     iyon
    0.50
    yntaxException
    0.50
    Activations Density 0.476%

    No Known Activations