© 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. 8933
    Prev
    Next
    INDEX
    Explanations

    references to legal procedures and their requirements

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

    the verb "is" appearing in formal or technical document contexts.

    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
    ⓧ
    -0.47
    úgó
    -0.42
     <<<<<<<<<<<<<<
    -0.40
    Diweddarwch
    -0.39
     considér
    -0.37
     nahilalakip
    -0.35
     yanı
    -0.35
    Открыть
    -0.35
    Suara
    -0.34
    ckså
    -0.33
    POSITIVE LOGITS
     depicted
    1.84
     portrayed
    1.65
     represented
    1.55
     described
    1.52
     shown
    1.40
     listed
    1.34
     outlined
    1.31
     contained
    1.30
     featured
    1.30
     reflected
    1.28
    Activations Density 1.635%

    No Known Activations