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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 13-GEMMASCOPE-RES-16K
    6. 10654
    Prev
    Next
    INDEX
    Explanations

    the repetition of the word "several"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     prez
    -0.76
    zuki
    -0.70
     Miki
    -0.64
     rego
    -0.63
     Kearney
    -0.62
     råd
    -0.60
     it
    -0.59
     creeds
    -0.56
    k
    -0.56
    <h2>
    -0.56
    POSITIVE LOGITS
     '{@
    1.16
     Plusieurs
    1.08
     mehrerer
    1.05
    veral
    1.03
     CreateTagHelper
    0.98
    several
    0.98
    ····
    0.97
     dozen
    0.97
    Varios
    0.96
    ihnachten
    0.96
    Activations Density 0.060%

    No Known Activations