© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 16066
    Prev
    Next
    INDEX
    Explanations

    key phrases related to statistical or analytical data indicators

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -1.02
     BoxFit
    -1.00
     Administrativna
    -0.99
     мәкал
    -0.98
     Италијани
    -0.88
    Geplaatst
    -0.88
     InputDecoration
    -0.87
    StoryboardSegue
    -0.87
     ComVisible
    -0.86
     nakalista
    -0.85
    POSITIVE LOGITS
      
    0.73
    ).
    0.62
    <b>
    0.61
    ↵
    0.61
    </b>
    0.61
    ),
    0.60
    <u>
    0.60
    <sup>
    0.59
    </strong>
    0.56
    )
    0.56
    Activations Density 0.166%

    No Known Activations