© 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. 18-GEMMASCOPE-RES-16K
    11. 10753
    Prev
    Next
    INDEX
    Explanations

    phrases related to injury and victimization

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

    Locations: streets, roadsides, sidewalks

    np_acts-logits-general · gemini-2.0-flash

    street, sidewalk, or roadside

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aDecoder
    -0.53
    pielt
    -0.50
    TabIndex
    -0.44
    kula
    -0.43
     <>",
    -0.42
    lani
    -0.41
     einger
    -0.41
    進去
    -0.40
    vaného
    -0.40
     ويكيميديا
    -0.39
    POSITIVE LOGITS
     street
    1.74
     streets
    1.66
    street
    1.46
     Straßen
    1.34
    Street
    1.34
     roadside
    1.34
     STREET
    1.31
    STREET
    1.28
    streets
    1.27
     sidewalk
    1.25
    Activations Density 0.150%

    No Known Activations