© 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. 6-GEMMASCOPE-RES-16K
    6. 11947
    Prev
    Next
    INDEX
    Explanations

    elements of mathematical expressions and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MOC
    -0.84
    ########.
    -0.83
     Bogen
    -0.81
    rubin
    -0.81
     Greenberg
    -0.79
     Schultz
    -0.78
     Stein
    -0.76
    MOC
    -0.73
     McMillan
    -0.72
     Teich
    -0.71
    POSITIVE LOGITS
    _{\
    1.77
     }_{\
    1.53
    }_{\
    1.45
    )_{\
    1.32
     _{\
    1.29
    }}_{\
    1.16
    ]_{\
    1.06
    \|_{\
    0.94
     $_{\
    0.92
     Kingfisher
    0.89
    Activations Density 0.211%

    No Known Activations