© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 3893
    Prev
    Next
    INDEX
    Explanations

    terms related to medical treatments and conditions, particularly focusing on specific medications and symptoms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.79
     nonatomic
    -0.65
     CreateTagHelper
    -0.63
     defStyleAttr
    -0.56
    AndEndTag
    -0.54
    oa̍t
    -0.53
    帖最后由
    -0.50
     Signalez
    -0.49
    BoxShadow
    -0.48
    tagPool
    -0.48
    POSITIVE LOGITS
    工
    0.39
    WriteTagHelper
    0.37
     Opportun
    0.32
    avyzd
    0.32
     עוב
    0.31
     IFTT
    0.31
    htdocs
    0.31
     Naidu
    0.30
    Opportun
    0.30
    bisch
    0.30
    Activations Density 2.543%

    No Known Activations