© 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. 28-GEMMASCOPE-RES-16K
    11. 9810
    Prev
    Next
    INDEX
    Explanations

    terms related to weight, weight management, and obesity

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

    "weight" and its changes

    np_acts-logits-general · gemini-2.0-flash

    weight change, gain, loss

    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
    afficheront
    -0.59
    ScopeManager
    -0.53
     виправивши
    -0.52
     betweenstory
    -0.50
     mostrarán
    -0.50
    hoeddwyd
    -0.49
    utilisons
    -0.49
    úrese
    -0.47
    TestingModule
    -0.46
     Roskov
    -0.46
    POSITIVE LOGITS
    weight
    0.90
    Weight
    0.89
     weight
    0.86
     Weight
    0.84
    WEIGHT
    0.83
     WEIGHT
    0.82
    weights
    0.72
     weights
    0.69
     Weights
    0.68
     Weigh
    0.67
    Activations Density 0.328%

    No Known Activations