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. 2-GEMMASCOPE-RES-16K
    6. 15808
    Prev
    Next
    INDEX
    Explanations

    negative sentiments and criticisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    itect
    -0.66
    뜻
    -0.59
    enn
    -0.56
     vapor
    -0.56
     semula
    -0.55
    CHAP
    -0.55
    фигу
    -0.54
    ENCH
    -0.52
    TUAL
    -0.52
     solder
    -0.52
    POSITIVE LOGITS
    ">-
    1.04
    Capítulo
    0.95
    awtextra
    0.94
     disambiguazione
    0.93
    //-
    0.89
     nahilalakip
    0.88
    \{\\
    0.88
    >-</
    0.87
    {-
    0.84
     -
    0.84
    Activations Density 0.432%

    No Known Activations