© 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. 0-GEMMASCOPE-RES-16K
    6. 7348
    Prev
    Next
    INDEX
    Explanations

    references to cars and automotive-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    shadowOffset
    -0.60
     margiela
    -0.55
    ']));
    -0.54
     Soit
    -0.54
     recém
    -0.54
     encantó
    -0.54
    ſelves
    -0.54
     ſt
    -0.53
    vskip
    -0.53
    }});
    -0.53
    POSITIVE LOGITS
     car
    2.31
     Car
    2.24
    Car
    2.12
    car
    2.10
     cars
    1.56
     CAR
    1.47
    cars
    1.46
     Cars
    1.41
    CAR
    1.36
    Cars
    1.17
    Activations Density 0.158%

    No Known Activations