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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 21-GEMMASCOPE-RES-16K
    6. 15215
    Prev
    Next
    INDEX
    Explanations

    sequences of underscores, indicating the presence of placeholders or gaps in the text

    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
    kháu
    -0.64
    onOptions
    -0.62
    afficheront
    -0.60
     JpaRepository
    -0.59
    IsUnicode
    -0.55
    addContainerGap
    -0.54
     conservé
    -0.54
     diarias
    -0.53
    awtextra
    -0.53
     mostrarán
    -0.53
    POSITIVE LOGITS
    tagHelper
    0.70
    帖最后由
    0.62
    inkle
    0.60
    Kaieteur
    0.57
    atase
    0.56
    "=>$
    0.55
     Hetero
    0.55
     cư
    0.54
    vák
    0.53
     وتسجيلات
    0.53
    Activations Density 0.027%

    No Known Activations