© 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. 13-GEMMASCOPE-RES-16K
    11. 6928
    Prev
    Next
    INDEX
    Explanations

    references to indeterminate or vague concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_13/width_16k/average_l0_132
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portály
    -0.62
     Füßen
    -0.61
     vettoriale
    -0.60
     betrekking
    -0.59
     oč
    -0.59
     kautta
    -0.57
     oídos
    -0.56
     rač
    -0.56
     mijne
    -0.56
    šech
    -0.54
    POSITIVE LOGITS
     something
    1.29
    Something
    1.21
     someone
    1.17
     Something
    1.16
    something
    1.15
    someone
    1.12
    Someone
    1.11
     SOMETHING
    1.09
     Someone
    1.05
     SOMEONE
    1.01
    Activations Density 0.109%

    No Known Activations