© 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. 9723
    Prev
    Next
    INDEX
    Explanations

    references to elements of religious beliefs or spirituality

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

    dialogue and conversational exchanges 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
    rungsseite
    -0.90
     kasarigan
    -0.87
    IsMutable
    -0.86
    AutoScaleMode
    -0.85
    AsUp
    -0.84
    SourceChecksum
    -0.83
     pungkas
    -0.82
    sidemargin
    -0.81
    SharedDtor
    -0.79
    已然
    -0.79
    POSITIVE LOGITS
     people
    0.66
     lots
    0.58
    Lots
    0.57
     différent
    0.56
     everybody
    0.53
     because
    0.53
    いろいろな
    0.52
     different
    0.52
     différente
    0.50
     diferente
    0.49
    Activations Density 4.401%

    No Known Activations