© 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. 23-GEMMASCOPE-RES-16K
    11. 14607
    Prev
    Next
    INDEX
    Explanations

    numbers or numerical data, particularly in various contexts or formats

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MigrationBuilder
    -0.70
    tagHelper
    -0.53
     int
    -0.50
    PLANE
    -0.47
     alene
    -0.44
    RegistryLite
    -0.43
    TabIndex
    -0.42
    hata
    -0.42
     IndexPath
    -0.41
     not
    -0.41
    POSITIVE LOGITS
     kaarangay
    0.78
     Мексичка
    0.75
     فريبيس
    0.71
    OGND
    0.70
     تانيه
    0.68
     للاسماء
    0.66
     xenia
    0.66
    __":
    0.66
    </caption>
    0.64
    <bos>
    0.64
    Activations Density 0.321%

    No Known Activations