© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 468
    Prev
    Next
    INDEX
    Explanations

    research-related concepts and actions that involve investigation, assessment, and improvement in various contexts

    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
     the
    -0.77
    <bos>
    -0.69
    2
    -0.55
    this
    -0.54
    1
    -0.54
     this
    -0.52
     ibunya
    -0.52
     másik
    -0.51
    '
    -0.51
    这个
    -0.51
    POSITIVE LOGITS
    ^(@
    1.20
    Portale
    1.16
    olesale
    1.09
    ^(@)
    1.09
     snippetHide
    1.04
     CURIAM
    0.99
    ſelves
    0.97
     ―――――
    0.97
     $_"
    0.95
     various
    0.93
    Activations Density 1.276%

    No Known Activations