© 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-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 800
    Prev
    Next
    INDEX
    Explanations

    references to vectors and their properties in a mathematical or programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    はじめに
    -0.62
    Personensuche
    -0.62
    AppMethodBeat
    -0.61
    pausal
    -0.58
    momix
    -0.49
     intu
    -0.48
    enterOuterAlt
    -0.47
    WhereInput
    -0.46
    }\}
    -0.46
    ."]
    -0.46
    POSITIVE LOGITS
    Degree
    0.98
    degree
    0.89
    deg
    0.89
    vec
    0.86
     Degrees
    0.83
     Degree
    0.83
     degree
    0.79
     degrees
    0.76
    degrees
    0.75
    Deg
    0.72
    Activations Density 0.086%

    No Known Activations