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. 11-GEMMASCOPE-RES-16K
    6. 6602
    Prev
    Next
    INDEX
    Explanations

    HTML and JSON-related markup and elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     appunto
    -0.55
    ↵↵
    -0.48
    .
    -0.47
    The
    -0.44
    <h2>
    -0.42
    Although
    -0.42
    But
    -0.42
    <eos>
    -0.41
     alábbi
    -0.41
     say
    -0.41
    POSITIVE LOGITS
     surla
    1.03
    OGND
    0.98
    Географи
    0.97
    Geplaatst
    0.95
     незавершена
    0.94
     Roskov
    0.92
     Савезне
    0.86
    bootstrapcdn
    0.84
    はじめに
    0.84
     nahilalakip
    0.84
    Activations Density 0.887%

    No Known Activations