© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 19-GEMMASCOPE-RES-16K
    6. 4738
    Prev
    Next
    INDEX
    Explanations

    conditional statements and user input handling in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    StoreMessageInfo
    -0.76
    CppMethod
    -0.74
    UnsafeEnabled
    -0.68
    Pautan
    -0.66
     للمعارف
    -0.66
     protoimpl
    -0.63
     linkovi
    -0.62
    QRST
    -0.62
    IndentedString
    -0.61
    ActiveRecord
    -0.60
    POSITIVE LOGITS
    putnik
    0.56
    ussis
    0.55
    ='
    0.48
    uncher
    0.47
     nang
    0.46
    FXML
    0.45
     '
    0.45
    eson
    0.43
    پاسخ
    0.42
    ']='
    0.42
    Activations Density 0.183%

    No Known Activations