© 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. 15-GEMMASCOPE-RES-16K
    11. 2251
    Prev
    Next
    INDEX
    Explanations

    specific scientific and technical terms related to algorithms and classification methods

    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
    setVerticalGroup
    -0.54
     utafitiHapana
    -0.48
    tagext
    -0.47
    Vaata
    -0.45
     дописавши
    -0.44
    agisse
    -0.44
    ništ
    -0.43
     lenker
    -0.43
    ivores
    -0.43
    irvana
    -0.43
    POSITIVE LOGITS
    ########.
    0.45
     technique
    0.43
     techniques
    0.41
     <=",
    0.40
     Catholicism
    0.38
     Hath
    0.38
     Gallup
    0.37
     hydropon
    0.37
    やり
    0.35
    法
    0.35
    Activations Density 1.859%

    No Known Activations