Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 11924
    Prev
    Next
    INDEX
    Explanations

    specific biological or botanical terms related to species classification

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

    Japanese language related

    np_acts-logits-general · gemini-2.0-flash

    Latin scientific names and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bann
    -0.44
    SBATCH
    -0.43
    toMatchSnapshot
    -0.42
    stro
    -0.42
    3
    -0.41
    =”
    -0.41
     cus
    -0.41
    mény
    -0.40
    metto
    -0.40
     Davi
    -0.39
    POSITIVE LOGITS
     ressemb
    0.77
     leksikon
    0.77
     GenerationType
    0.73
    letal
    0.73
    laceae
    0.73
    ellees
    0.71
     LoggerFactory
    0.70
     ldc
    0.69
     révé
    0.67
    letons
    0.66
    Activations Density 0.342%

    No Known Activations