© 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. 11432
    Prev
    Next
    INDEX
    Explanations

    formal definitions and logical constructs in scientific contexts

    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
    ளை
    -0.67
     slice
    -0.60
    Rohy
    -0.59
     صوتيه
    -0.59
     beginnetje
    -0.57
     slices
    -0.56
    ilerini
    -0.55
     colpo
    -0.55
    enziale
    -0.54
    stylers
    -0.54
    POSITIVE LOGITS
     that
    0.82
     realizes
    0.78
     notare
    0.70
    Напомним
    0.69
     bahwa
    0.67
     RequestMethod
    0.67
    obacz
    0.67
     OGS
    0.67
     realizing
    0.66
     realize
    0.66
    Activations Density 1.201%

    No Known Activations