© 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. 24-GEMMASCOPE-RES-16K
    6. 4700
    Prev
    Next
    INDEX
    Explanations

    features and functionalities related to car performance and safety technology

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

    driving

    np_acts-logits-general · gemini-2.0-flash

    driving and driver

    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
    énage
    -0.54
    MenuInflater
    -0.49
    Publica
    -0.48
    NOPQRST
    -0.48
    VersionUID
    -0.47
     cherchez
    -0.47
    ]-->
    -0.46
    Jsp
    -0.45
    heon
    -0.44
    caches
    -0.44
    POSITIVE LOGITS
     driving
    2.91
     driver
    2.75
     drive
    2.67
    driving
    2.60
     Driving
    2.56
     drivers
    2.52
    Driving
    2.51
     drives
    2.48
    driver
    2.40
     Driver
    2.38
    Activations Density 0.289%

    No Known Activations