© 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. 8-GEMMASCOPE-RES-16K
    6. 5188
    Prev
    Next
    INDEX
    Explanations

    code-related syntax and keywords, particularly those associated with assembly attributes and metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Extinguishing
    -0.58
    bitField
    -0.56
    UnknownFieldSet
    -0.53
    quio
    -0.48
     viewType
    -0.48
    FieldDescriptor
    -0.47
    SwingConstants
    -0.46
     tied
    -0.44
     $__
    -0.43
     inti
    -0.43
    POSITIVE LOGITS
     }</
    0.73
    ]$}
    0.64
    <?
    0.63
     RIPRODUZIONE
    0.62
    berdayakan
    0.61
     gentes
    0.60
    cerely
    0.60
     málaga
    0.60
    aians
    0.60
    (!__
    0.59
    Activations Density 0.489%

    No Known Activations