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. 5-GEMMASCOPE-RES-16K
    6. 10997
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Italijanski
    -0.81
     архивлан
    -0.79
     ModelExpression
    -0.76
    SerializedSize
    -0.76
    CloseOperation
    -0.74
     Audiodateien
    -0.73
    riwal
    -0.72
    GRANTED
    -0.72
    Jeografia
    -0.71
    HasForeignKey
    -0.66
    POSITIVE LOGITS
    Égypte
    0.43
    ására
    0.42
    ườ
    0.41
     AssemblyCompany
    0.41
    almaz
    0.41
     laſt
    0.40
    BufferException
    0.40
    通用
    0.40
    indépendance
    0.40
     Daß
    0.40
    Activations Density 0.150%

    No Known Activations