© 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. 4-GEMMASCOPE-RES-16K
    11. 1704
    Prev
    Next
    INDEX
    Explanations

    geographical and infrastructural references related to highways and road systems

    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
     viewType
    -0.51
    preduce
    -0.48
    PullParser
    -0.46
    RunWith
    -0.44
     instance
    -0.44
    StartTag
    -0.42
    scryfall
    -0.42
    ◁
    -0.42
    enumi
    -0.41
     personales
    -0.40
    POSITIVE LOGITS
     highway
    1.55
     Highway
    1.47
     highways
    1.45
     HIGHWAY
    1.36
    highway
    1.34
     motorway
    1.34
    Highway
    1.30
     Hwy
    1.29
     freeway
    1.25
     Freeway
    1.25
    Activations Density 0.352%

    No Known Activations