© 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. 2842
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "first" and other ordinal indicators

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

    ordinal positions or sequential references to initial items (first, second, third).

    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
    further
    -0.45
    AGAIN
    -0.42
     selanjutnya
    -0.42
     diesmal
    -0.41
     vidare
    -0.40
     τελευτα
    -0.40
     içerisinde
    -0.40
    ControllerAdvice
    -0.39
     antemano
    -0.39
     ulang
    -0.38
    POSITIVE LOGITS
     two
    0.93
     few
    0.82
     three
    0.74
     portion
    0.63
     beiden
    0.62
     part
    0.60
     half
    0.59
     four
    0.57
     couple
    0.55
     several
    0.54
    Activations Density 0.322%

    No Known Activations