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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9519
    Prev
    Next
    INDEX
    Explanations

    HTML or JSX elements and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Geplaatst
    -0.66
     gepubliceerd
    -0.54
    autoIncrement
    -0.54
     Bland
    -0.53
    mybatisplus
    -0.52
     “
    -0.50
    clusion
    -0.49
    :✨
    -0.49
    TRAILING
    -0.48
     perd
    -0.47
    POSITIVE LOGITS
    __*/
    0.76
    Datuak
    0.74
     className
    0.67
    </caption>
    0.66
    )':
    0.63
    ."]
    0.63
    ########.
    0.63
    ValueStyle
    0.62
    \{\\
    0.61
    PrototypeOf
    0.61
    Activations Density 0.014%

    No Known Activations