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. 4868
    Prev
    Next
    INDEX
    Explanations

    references to poetry and poetic forms

    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
    //
    -0.88
    setBounds
    -0.69
     estimés
    -0.67
    ConstraintMaker
    -0.65
    }^{(
    -0.64
    NegativeButton
    -0.61
    ssus
    -0.60
     NUKAT
    -0.60
    prnewswire
    -0.59
     ReactDOM
    -0.58
    POSITIVE LOGITS
     poetry
    2.25
     poems
    2.07
     poem
    2.02
     Poetry
    1.92
    Poetry
    1.85
    poetry
    1.84
     Poem
    1.80
     poet
    1.79
     poets
    1.68
     Poet
    1.66
    Activations Density 0.058%

    No Known Activations