© 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. 497
    Prev
    Next
    INDEX
    Explanations

    notable individuals and their roles or contributions in various fields

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

    before commas

    np_acts-logits-general · gemini-2.0-flash

    names ending in ling, on, ner, ie, cer, ley

    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
    httphttps
    -0.89
    verwijspagina
    -0.84
    Tembelea
    -0.80
     الحره
    -0.79
    StructEnd
    -0.79
     BoxFit
    -0.79
    下载附件
    -0.78
    
    -0.78
    ConstraintMaker
    -0.73
    enderror
    -0.72
    POSITIVE LOGITS
     and
    0.44
     who
    0.43
    who
    0.35
    pos
    0.34
     вспом
    0.32
    .
    0.31
     recalled
    0.30
    fl
    0.30
     bordo
    0.29
     benda
    0.28
    Activations Density 0.197%

    No Known Activations