© 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. 3-GEMMASCOPE-RES-16K
    11. 9249
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notation used in equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.81
    putan
    -0.69
    aarrggbb
    -0.68
    principalColumn
    -0.68
     EconPapers
    -0.63
    OGND
    -0.60
     joaat
    -0.59
     autorytatywna
    -0.58
    Diwedd
    -0.57
    protoc
    -0.57
    POSITIVE LOGITS
    ])))
    0.72
    InstrumentedTest
    0.68
    ])):
    0.57
    "]))
    0.57
    ↵↵↵↵↵↵
    0.56
    </h6>
    0.55
    </h5>
    0.55
    "]));
    0.54
    ↵↵↵
    0.54
    </h2>
    0.53
    Activations Density 0.148%

    No Known Activations