© 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. 14-GEMMASCOPE-RES-16K
    6. 6821
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and data manipulation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OrNil
    -0.57
    +#+
    -0.56
    splitlines
    -0.47
    Попис
    -0.46
     surla
    -0.46
    IContainer
    -0.45
    LogFactory
    -0.43
    ContentAsync
    -0.41
    poko
    -0.41
    PreExecute
    -0.40
    POSITIVE LOGITS
     transfer
    1.10
     transferring
    1.06
     transfers
    1.04
     Transfer
    1.02
    transfer
    0.99
     between
    0.98
     transferência
    0.96
     TRANSFER
    0.96
    Transfer
    0.96
     transferir
    0.93
    Activations Density 0.874%

    No Known Activations