© 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. 5-GEMMASCOPE-RES-16K
    11. 3253
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to logic circuits and Boolean algebra

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.69
    glGen
    -0.49
     zwy
    -0.48
     stället
    -0.48
     عج
    -0.47
     nemlig
    -0.47
    自助
    -0.47
     unanimously
    -0.47
    !*\
    -0.46
     Microb
    -0.45
    POSITIVE LOGITS
    OGND
    0.91
     Boolean
    0.89
    Boolean
    0.82
     logic
    0.80
    putBoolean
    0.77
    цездатний
    0.74
     logique
    0.71
    logic
    0.71
    BOOLEAN
    0.70
    Bool
    0.69
    Activations Density 0.809%

    No Known Activations