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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 4775
    Prev
    Next
    INDEX
    Explanations

    chemical and mathematical terms related to composition and processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <eos>
    -0.50
     }}</
    -0.46
     almost
    -0.45
    }}</
    -0.44
    ↵↵
    -0.43
     position
    -0.43
    ())))
    -0.43
     ApiException
    -0.42
    *)((
    -0.42
    

    -0.41
    POSITIVE LOGITS
    _{
    1.14
     }_{
    1.13
     $_{
    1.04
    $_{
    1.00
     subscript
    0.99
    _{\
    0.98
    }_{
    0.96
     _{
    0.96
    )_{
    0.95
     }_{\
    0.92
    Activations Density 1.332%

    No Known Activations