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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 16095
    Prev
    Next
    INDEX
    Explanations

    references to requests and capabilities related to geospatial services

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

    map layers or geospatial data

    np_acts-logits-general · gemini-2.0-flash

    layers and features

    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
    +#+
    -0.60
    DebuggerStep
    -0.60
    Demografie
    -0.57
    httphttps
    -0.57
     conjugation
    -0.54
     linkovi
    -0.54
     initComponents
    -0.53
    parsedMessage
    -0.53
     MenuView
    -0.51
    rials
    -0.51
    POSITIVE LOGITS
     layer
    1.00
    layer
    0.93
    Layer
    0.92
     Layer
    0.91
    Feature
    0.88
     Feature
    0.87
     feature
    0.84
     layers
    0.84
    feature
    0.80
     ge
    0.77
    Activations Density 0.172%

    No Known Activations