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. 1-GEMMASCOPE-RES-16K
    6. 7259
    Prev
    Next
    INDEX
    Explanations

    references to 'ft' or related terms, likely related to a specific technology or framework

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iented
    -0.72
    gonic
    -0.64
    $_['
    -0.63
    aarrggbb
    -0.63
    colorPrimary
    -0.63
    ﴿
    -0.62
     demografica
    -0.61
    ICTO
    -0.61
     Nath
    -0.61
    :].
    -0.61
    POSITIVE LOGITS
    ft
    4.23
    FT
    3.38
     ft
    3.20
     FT
    2.61
    Ft
    2.33
    fts
    2.01
     Ft
    1.91
    fting
    1.76
    FTS
    1.49
    fta
    1.47
    Activations Density 0.088%

    No Known Activations