© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 5919
    Prev
    Next
    INDEX
    Explanations

    terms related to visual elements and their characteristics

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

    "Visual" followed by other words

    np_acts-logits-general · gemini-2.0-flash

    Visual compounds or phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.65
     vocale
    -0.56
    protoimpl
    -0.55
    getSeconds
    -0.52
    useNewUrlParser
    -0.52
     ControllerBase
    -0.51
    ệp
    -0.50
     volontaire
    -0.50
    adays
    -0.50
     décé
    -0.50
    POSITIVE LOGITS
     aids
    0.74
     acuity
    0.72
     aid
    0.62
     cues
    0.61
    izer
    0.60
     impairment
    0.59
     representation
    0.59
     impaired
    0.58
     kei
    0.57
    paque
    0.56
    Activations Density 0.085%

    No Known Activations