Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 10078
    Prev
    Next
    INDEX
    Explanations

    terms related to logical operations or conditions in programming

    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
    })()
    -0.58
    orrhea
    -0.52
    rady
    -0.51
    Marne
    -0.50
     Elke
    -0.50
    rippa
    -0.49
    getError
    -0.49
    "");
    -0.49
    urgia
    -0.49
     isInitialized
    -0.48
    POSITIVE LOGITS
    stdc
    0.74
    lector
    0.64
    érateur
    0.64
    rador
    0.62
    новниш
    0.61
    AccessorTable
    0.60
    ador
    0.60
    SequentialGroup
    0.58
    icator
    0.57
    itor
    0.57
    Activations Density 0.424%

    No Known Activations