© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 8249
    Prev
    Next
    INDEX
    Explanations

    research-related terms indicating the need for prospective studies in a multi-center or observational context

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

    Types of clinical research studies

    np_acts-logits-general · gemini-2.0-flash

    prospective randomized studies

    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
    PLANATION
    -0.41
    HttpPut
    -0.38
    GARET
    -0.36
    министра
    -0.35
    nosaurus
    -0.34
     puntas
    -0.34
    wikk
    -0.34
     extrême
    -0.34
     Италијани
    -0.34
    égories
    -0.33
    POSITIVE LOGITS
     studies
    1.15
     study
    1.10
    studies
    1.00
     Study
    0.95
     Studies
    0.94
    study
    0.90
    Studies
    0.89
    Study
    0.87
     estudios
    0.87
     randomized
    0.85
    Activations Density 1.663%

    No Known Activations