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. 12-GEMMASCOPE-RES-16K
    6. 15479
    Prev
    Next
    INDEX
    Explanations

    parentheses and their usage in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fromnode
    -0.59
     and
    -0.52
     or
    -0.51
    </strong>
    -0.51
     Here
    -0.51
    diye
    -0.50
    </em>
    -0.50
     betweenstory
    -0.48
    ‑
    -0.48
    vaig
    -0.48
    POSITIVE LOGITS
     }^{(
    1.21
    Geplaatst
    1.02
    ={(
    0.93
    Hozzáférés
    0.91
     Савезне
    0.91
    ',(
    0.89
    ]=(
    0.88
    )(((
    0.88
    >((
    0.87
    [(
    0.86
    Activations Density 0.096%

    No Known Activations