© 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. 18-GEMMASCOPE-RES-16K
    6. 9708
    Prev
    Next
    INDEX
    Explanations

    variables related to configuration settings in software code

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

    Environment variable names

    np_acts-logits-general · gemini-2.0-flash

    environment variables

    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
    #+#
    -0.62
     însă
    -0.52
    DECREF
    -0.52
     khiển
    -0.52
     lâng
    -0.51
     pistons
    -0.51
     createState
    -0.51
    ScopeManager
    -0.51
    anguages
    -0.50
    siery
    -0.50
    POSITIVE LOGITS
     environment
    0.83
     env
    0.81
    env
    0.80
     Environment
    0.77
    environment
    0.77
    Environment
    0.75
    Env
    0.74
    dotenv
    0.74
     ENV
    0.73
     dotenv
    0.73
    Activations Density 0.267%

    No Known Activations