© 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. 6798
    Prev
    Next
    INDEX
    Explanations

    statements related to expectation or future predictions, particularly in the context of sports outcomes

    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
    WriteLiteral
    -0.53
     indipendente
    -0.50
     pratique
    -0.49
    勁
    -0.49
    yez
    -0.49
    ान्त
    -0.48
     practise
    -0.48
     prati
    -0.48
     my
    -0.48
     colheres
    -0.47
    POSITIVE LOGITS
    AttributeSet
    0.77
    verwijspagina
    0.69
    GraphicsUnit
    0.67
    raisemb
    0.62
     Wednesday
    0.59
     AssemblyCulture
    0.59
     flashed
    0.58
    queryInterface
    0.58
    åringen
    0.57
     Thursday
    0.56
    Activations Density 0.273%

    No Known Activations