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. 3-GEMMASCOPE-RES-16K
    6. 7546
    Prev
    Next
    INDEX
    Explanations

    expressions indicating alternatives or substitutes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.94
    InputBorder
    -0.92
    dymyr
    -0.84
    expandindo
    -0.83
    TagMode
    -0.82
    #+#
    -0.82
    Démographie
    -0.81
    NgModule
    -0.78
    ugier
    -0.76
    MLLoader
    -0.73
    POSITIVE LOGITS
     alternative
    3.48
     Alternative
    3.29
    Alternative
    3.25
     alternatives
    3.16
    alternative
    3.06
     Alternatives
    2.90
     ALTERNATIVE
    2.82
    Alternatives
    2.73
     alternativa
    2.71
     ALTERN
    2.62
    Activations Density 0.082%

    No Known Activations