© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 10532
    Prev
    Next
    INDEX
    Explanations

    HTML and markup language syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
    </h6>
    -0.84
    </h2>
    -0.83
    </h3>
    -0.69
     snippetHide
    -0.66
    </h5>
    -0.65
    Aiheesta
    -0.64
    pecabe
    -0.64
     ujednoznacz
    -0.62
    </h1>
    -0.62
     desmotivaciones
    -0.60
    POSITIVE LOGITS
    s
    0.41
     absolute
    0.37
    stateMutability
    0.33
    ra
    0.32
     (
    0.32
    te
    0.32
     ار
    0.32
    ac
    0.32
    ReferenceEquals
    0.32
    da
    0.32
    Activations Density 0.022%

    No Known Activations