© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 14158
    Prev
    Next
    INDEX
    Explanations

    LaTeX formatting and mathematical notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.63
     betweenstory
    -0.53
    Personendaten
    -0.51
    +#+#
    -0.47
     concern
    -0.47
    twimg
    -0.45
     wireType
    -0.45
     relations
    -0.45
    duga
    -0.45
     الوطنيه
    -0.44
    POSITIVE LOGITS
     ddelweddau
    0.67
     propOrder
    0.65
    AutoField
    0.63
     \]
    0.61
     onBind
    0.61
    braith
    0.59
     Theſe
    0.58
    Portály
    0.58
     InputDecoration
    0.58
    wapV
    0.57
    Activations Density 0.088%

    No Known Activations