© 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. 9512
    Prev
    Next
    INDEX
    Explanations

    information regarding reality television and its contestants

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

    names of celebrities and public figures, particularly in contexts describing their legal troubles or public scandals.

    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
     elástica
    -0.53
    lapsingToolbar
    -0.50
    帖最后由
    -0.48
     Италијани
    -0.47
     florales
    -0.46
     estatua
    -0.46
     resourceCulture
    -0.45
     stället
    -0.45
     Sorten
    -0.45
     infância
    -0.45
    POSITIVE LOGITS
     Bigg
    0.71
     Reality
    0.65
     reality
    0.64
     house
    0.60
     House
    0.57
     evicted
    0.57
     Big
    0.57
     BB
    0.56
    Reality
    0.54
     eviction
    0.53
    Activations Density 0.049%

    No Known Activations