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. 21-GEMMASCOPE-RES-16K
    6. 1996
    Prev
    Next
    INDEX
    Explanations

    the word "by" and its variations, indicating attributions or authorship

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    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
    -0.69
     both
    -0.69
     a
    -0.67
    ÁND
    -0.65
    taler
    -0.64
    짐
    -0.61
    ielsen
    -0.60
    hæng
    -0.59
     an
    -0.59
     either
    -0.58
    POSITIVE LOGITS
    ंदीखरीदारी
    0.75
    +#+#
    0.67
     виправивши
    0.62
    tagHelperRunner
    0.59
    BeginInit
    0.55
    y
    0.54
    AxisAlignment
    0.52
    #+#
    0.51
     RSSSF
    0.50
     disponibilités
    0.48
    Activations Density 0.102%

    No Known Activations