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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12023
    Prev
    Next
    INDEX
    Explanations

    medical terms related to conditions and treatments

    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
    期刊论文
    -0.55
     PeEnEo
    -0.50
    gemeen
    -0.48
     whoſe
    -0.48
     sukienka
    -0.48
     löytyy
    -0.48
    hithe
    -0.47
     takže
    -0.47
    ſem
    -0.46
     recibo
    -0.46
    POSITIVE LOGITS
     compared
    0.65
    compared
    0.53
     Compared
    0.50
    Compared
    0.49
     versus
    0.47
     comparison
    0.44
    Hentet
    0.43
     vs
    0.42
     jäm
    0.40
     Comparison
    0.39
    Activations Density 2.358%

    No Known Activations