© 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. 15438
    Prev
    Next
    INDEX
    Explanations

    references to professional roles and transitions

    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
    CrossRef
    -0.69
     baseman
    -0.59
    UnknownFields
    -0.57
     fallait
    -0.56
    timeter
    -0.53
    WebMethod
    -0.48
     cumplido
    -0.48
    avras
    -0.47
    béco
    -0.46
     baptized
    -0.46
    POSITIVE LOGITS
     journalism
    1.34
     politics
    1.32
     medicine
    1.22
     photography
    1.15
     filmmaking
    1.14
     dentistry
    1.13
     economics
    1.07
    politics
    1.01
    medicine
    1.01
     agriculture
    1.00
    Activations Density 0.872%

    No Known Activations