© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 10645
    Prev
    Next
    INDEX
    Explanations

    references to tires and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     <<<<<<<<<<<<<<
    -0.61
    Personendaten
    -0.60
     Kral
    -0.58
    öl
    -0.57
    wezen
    -0.57
    erschrank
    -0.55
     TestBed
    -0.55
    хия
    -0.54
    லா
    -0.54
    rule
    -0.53
    POSITIVE LOGITS
     tires
    1.65
     tire
    1.50
     tyres
    1.49
     Tires
    1.47
     tyre
    1.40
    Tire
    1.38
     Tire
    1.36
    tires
    1.26
    Tires
    1.20
     pneus
    1.19
    Activations Density 0.136%

    No Known Activations