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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 8198
    Prev
    Next
    INDEX
    Explanations

    specific numeric values and identifiers in a structured data context

    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
    ate
    -0.43
    ated
    -0.40
     taban
    -0.39
     paid
    -0.39
     bocas
    -0.38
     daarvoor
    -0.38
     ni
    -0.37
    俏
    -0.36
     payed
    -0.36
     on
    -0.35
    POSITIVE LOGITS
    contentLoaded
    0.90
     للمعارف
    0.90
     ***!
    0.84
    Parcelize
    0.84
    ]")]
    0.83
    )');
    0.81
     vermelhas
    0.81
    expandindo
    0.80
    ########.
    0.79
     дописавши
    0.79
    Activations Density 0.043%

    No Known Activations