Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 1270
    Prev
    Next
    INDEX
    Explanations

    conjunctions and options in text

    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
     Shakspeare
    -1.03
     ―――――
    -0.97
     pleaſure
    -0.93
     purpoſe
    -0.91
     ſtate
    -0.91
     raiſ
    -0.89
     uſed
    -0.87
     ſever
    -0.86
     ftate
    -0.86
     ſame
    -0.85
    POSITIVE LOGITS
     and
    0.87
     And
    0.84
     Or
    0.83
     other
    0.81
     AND
    0.78
     OR
    0.74
     or
    0.69
     others
    0.68
     và
    0.68
     demás
    0.67
    Activations Density 0.209%

    No Known Activations