© 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. 4-GEMMASCOPE-RES-16K
    11. 1182
    Prev
    Next
    INDEX
    Explanations

    technical terms and functions related to data encoding and decoding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     viewType
    -0.79
     mView
    -0.76
     Stoner
    -0.73
     Offisielt
    -0.72
     AIAA
    -0.72
     Gerr
    -0.66
     كومونز
    -0.66
     ſtate
    -0.65
    standers
    -0.65
     Allez
    -0.65
    POSITIVE LOGITS
     encode
    2.85
    encode
    2.74
     encoding
    2.57
     encodes
    2.40
     Encode
    2.39
     encoded
    2.35
    Encode
    2.25
     Encoding
    2.23
    encoding
    2.18
    encoded
    2.10
    Activations Density 0.076%

    No Known Activations