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. 1-GEMMASCOPE-RES-16K
    6. 13356
    Prev
    Next
    INDEX
    Explanations

    terms related to biological and chemical processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fauci
    -0.51
    BeforeEach
    -0.45
     تضيفلها
    -0.45
    phils
    -0.43
    cinia
    -0.43
    Bane
    -0.43
    olah
    -0.42
    ふく
    -0.42
     Coronel
    -0.42
     ttk
    -0.42
    POSITIVE LOGITS
     fibers
    0.84
    fiber
    0.81
     Fibers
    0.76
    fibre
    0.76
     fiber
    0.76
     Alpine
    0.75
     fibres
    0.75
    
    0.72
     fibre
    0.72
    Fiber
    0.72
    Activations Density 2.313%

    No Known Activations