© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 27-GEMMASCOPE-RES-16K
    6. 10312
    Prev
    Next
    INDEX
    Explanations

    terms related to childhood obesity and nutritional deficiencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ārējās
    -0.57
    canestro
    -0.50
     Satisfied
    -0.46
    ########.
    -0.45
    delwed
    -0.44
     favourably
    -0.44
    RTEE
    -0.43
     Dzięki
    -0.43
    Satisfied
    -0.42
     benefited
    -0.42
    POSITIVE LOGITS
     worst
    1.05
    Worse
    1.04
     worse
    1.03
     Worse
    0.98
     worsened
    0.96
     worsening
    0.94
    worst
    0.91
     worsen
    0.91
     dangerous
    0.90
    worse
    0.90
    Activations Density 1.352%

    No Known Activations