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. 14-GEMMASCOPE-RES-16K
    6. 4124
    Prev
    Next
    INDEX
    Explanations

    expressions of doubt or questioning of statements and opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     élect
    -0.56
    httphttps
    -0.55
     élector
    -0.54
    ViewImports
    -0.53
     golpes
    -0.51
     Landis
    -0.51
     jacques
    -0.51
     pedimos
    -0.49
     nemlig
    -0.49
     brengen
    -0.48
    POSITIVE LOGITS
    MessageTagHelper
    0.70
    ?”.
    0.66
    ?</
    0.64
    ściej
    0.63
    ⓒ
    0.58
     Schön
    0.58
    ymce
    0.58
    ?".
    0.57
    )}{(
    0.57
    ?”
    0.57
    Activations Density 0.055%

    No Known Activations