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

    Neuronpedia

    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. 28-GEMMASCOPE-RES-16K
    11. 7446
    Prev
    Next
    INDEX
    Explanations

    scientific terms and phrases related to biological processes and experiments

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

    Pharmacology/receptor activation

    np_acts-logits-general · gemini-2.0-flash

    pharmacological action: block, induced, release, allow, via

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Попис
    -0.43
    BindingResult
    -0.42
     Angio
    -0.41
    enderror
    -0.40
    имущества
    -0.40
     alibi
    -0.40
     pector
    -0.40
     antisocial
    -0.39
     kasarigan
    -0.39
    windowFixed
    -0.38
    POSITIVE LOGITS
     Pharmacol
    0.53
     Pharmacology
    0.52
     Drogen
    0.51
     pharmacology
    0.49
     drogas
    0.48
     uyar
    0.48
     pharmaco
    0.47
     opening
    0.46
     leak
    0.44
     pharmacological
    0.43
    Activations Density 1.739%

    No Known Activations