© 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. 3601
    Prev
    Next
    INDEX
    Explanations

    references to cultural or religious celebrations and their significance

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

    Proper nouns and named entities, particularly place names and event titles.

    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
     Shet
    -0.39
     „
    -0.39
     costuras
    -0.38
    „
    -0.36
     equilibr
    -0.35
    Begriffsklä
    -0.34
     takže
    -0.33
     Ressource
    -0.33
     él
    -0.32
    ivably
    -0.32
    POSITIVE LOGITS
    EndProject
    0.57
     noDo
    0.50
    UrlResolution
    0.50
    Portail
    0.50
    󠁴
    0.49
     AssemblyCompany
    0.46
     astore
    0.46
    Corona
    0.46
    ########.
    0.45
    styleUrls
    0.45
    Activations Density 0.019%

    No Known Activations