© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 1822
    Prev
    Next
    INDEX
    Explanations

    specialized terminology and formatting commonly used in technical and scientific writing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    w
    -0.55
    S
    -0.50
    t
    -0.49
    <bos>
    -0.49
    G
    -0.49
    f
    -0.49
    x
    -0.46
    ca
    -0.46
    M
    -0.46
    T
    -0.46
    POSITIVE LOGITS
     تضيفلها
    1.25
     resourceCulture
    1.07
    ########.
    1.06
     Monfieur
    1.01
     Theſe
    0.99
     المعيارى
    0.99
     Мексичка
    0.98
     ExecuteAsync
    0.98
    ChildScrollView
    0.96
     ObjectParameter
    0.96
    Activations Density 1.033%

    No Known Activations