© 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. 24-GEMMASCOPE-RES-16K
    11. 547
    Prev
    Next
    INDEX
    Explanations

    elements related to organizations and their practices or challenges

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

    Comes before verbs like do, are, believe, arrive, and have

    np_acts-logits-general · gemini-2.0-flash

    many [entity type]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Controllo
    -0.37
    ghijkl
    -0.35
     protoimpl
    -0.35
    DIFF
    -0.34
     jät
    -0.33
     semua
    -0.31
     Waugh
    -0.31
    SharedModule
    -0.31
     հղումներ
    -0.31
     onlyOwner
    -0.31
    POSITIVE LOGITS
    webElementXpaths
    0.55
    SEGUIR
    0.52
     '\\;'
    0.50
    EndContext
    0.49
     underestimate
    0.48
    mergeFrom
    0.47
     nowadays
    0.46
     تعدى
    0.45
    rungsseite
    0.45
     Muchos
    0.45
    Activations Density 0.413%

    No Known Activations