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

    Neuronpedia

    APICircuit 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. 6204
    Prev
    Next
    INDEX
    Explanations

    structured data elements and metadata in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    clerview
    -0.75
    Filmographie
    -0.71
    ChildScrollView
    -0.69
    SequentialGroup
    -0.67
    SBATCH
    -0.66
    thyst
    -0.63
    alyptus
    -0.63
    culable
    -0.62
     kasarigan
    -0.60
    rhosis
    -0.60
    POSITIVE LOGITS
    Autoritní
    0.79
     Signalez
    0.60
    bootstrapcdn
    0.57
    الحياه
    0.55
    })));
    0.52
    WebVitals
    0.51
    Diweddarwch
    0.50
    zuf
    0.50
    WebElementEntity
    0.49
     Infórmanos
    0.48
    Activations Density 0.107%

    No Known Activations