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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 15-GEMMASCOPE-RES-16K
    6. 2838
    Prev
    Next
    INDEX
    Explanations

    terms related to organizational structure or governance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TagMode
    -0.73
     FetchType
    -0.66
    bootstrapcdn
    -0.60
     specchio
    -0.60
    OGND
    -0.57
    Portail
    -0.56
    +#+#
    -0.54
     incroy
    -0.54
    ʐ
    -0.53
     "..\..\
    -0.53
    POSITIVE LOGITS
     also
    1.77
     همچنین
    1.29
    also
    1.29
     также
    1.22
     Also
    1.17
     inoltre
    1.16
    Also
    1.16
     juga
    1.12
     ayrıca
    1.11
     furthermore
    1.11
    Activations Density 0.519%

    No Known Activations