© 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. 21-GEMMASCOPE-RES-16K
    6. 13359
    Prev
    Next
    INDEX
    Explanations

    discussions about historical accuracy and truthfulness

    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
     pinulongan
    -0.66
    ContentAsync
    -0.59
    SharedDtor
    -0.58
    ScopeManager
    -0.58
    yntaxException
    -0.58
    riwal
    -0.57
     invokingState
    -0.54
    stoke
    -0.51
     Testamento
    -0.51
     syner
    -0.50
    POSITIVE LOGITS
     reality
    3.13
    reality
    2.66
     Reality
    2.47
     realities
    2.37
    Reality
    2.34
     réalité
    2.31
     realidad
    2.29
     truth
    2.25
     realidade
    2.12
     Realität
    2.04
    Activations Density 0.425%

    No Known Activations