© 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. 526
    Prev
    Next
    INDEX
    Explanations

    interactions involving conflict and emotional exchanges

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

    physical confrontation and aggressive action between people.

    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
     متعلقه
    -0.56
     CreateTagHelper
    -0.53
    SourceChecksum
    -0.52
     CommonModule
    -0.47
    BeginContext
    -0.47
    󠁴
    -0.46
    WithIOException
    -0.45
     onAnimation
    -0.45
    BrowserModule
    -0.44
    AnimationsModule
    -0.43
    POSITIVE LOGITS
     back
    1.47
     reciproc
    1.31
     terug
    1.19
     return
    1.16
     returned
    1.15
     zurück
    1.13
    back
    1.11
     tillbaka
    1.11
     reply
    1.10
     retali
    1.06
    Activations Density 0.240%

    No Known Activations