© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 13296
    Prev
    Next
    INDEX
    Explanations

    numerical data and approximations in the context of statistics or research findings

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

    Preceding an estimate or approximation

    np_acts-logits-general · gemini-2.0-flash

    approximations and quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Jährige
    -0.71
     Numerade
    -0.55
    etheless
    -0.51
    ագրություններ
    -0.51
    AutoScaleMode
    -0.50
    "");
    -0.49
    orini
    -0.49
    ,))
    -0.48
    "])
    -0.48
    ool
    -0.48
    POSITIVE LOGITS
     midway
    0.83
     halfway
    0.80
     roughly
    0.71
     ungefär
    0.68
     approxim
    0.68
     dozen
    0.68
     approximated
    0.67
     aproximado
    0.64
     equidist
    0.64
    half
    0.64
    Activations Density 0.213%

    No Known Activations