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. 17-GEMMASCOPE-RES-16K
    6. 6188
    Prev
    Next
    INDEX
    Explanations

    elements related to simplicity and subtlety in design or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.57
     Waray
    -0.52
    textAppearance
    -0.51
    blond
    -0.47
    ADELPHIA
    -0.46
    elerik
    -0.45
    undial
    -0.45
     decreasing
    -0.45
    ABASES
    -0.45
    garage
    -0.44
    POSITIVE LOGITS
     nevertheless
    1.11
     nonetheless
    1.00
    theless
    0.92
    それでも
    0.84
     Nonetheless
    0.78
     dennoch
    0.78
    etheless
    0.76
    Nonetheless
    0.76
     pourtant
    0.76
     suffices
    0.75
    Activations Density 0.301%

    No Known Activations