Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 6397
    Prev
    Next
    INDEX
    Explanations

    terms related to medical procedures, women's health, and reproductive topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.54
    Попис
    -0.53
    Filmografia
    -0.52
     EconPapers
    -0.51
    Personendaten
    -0.51
    richTextPanel
    -0.50
    cookieParser
    -0.50
     téc
    -0.49
    HasForeignKey
    -0.49
    Dữ
    -0.46
    POSITIVE LOGITS
    RectangleBorder
    0.49
    __()
    0.46
    ölkerung
    0.44
     }}"></
    0.42
    évaluateur
    0.42
    دانشنامهٔ
    0.42
    ")));
    
    0.42
     <<<<<<<<<<<<<<
    0.41
    hidupan
    0.41
     Lumpur
    0.41
    Activations Density 2.111%

    No Known Activations