Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 14-GEMMASCOPE-RES-16K
    6. 10601
    Prev
    Next
    INDEX
    Explanations

    phrases indicating similarity or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/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.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onso
    -0.56
    es
    -0.56
    !("{
    -0.52
     Nase
    -0.50
     Græ
    -0.50
    lección
    -0.50
    arbox
    -0.50
     ulang
    -0.49
    といけない
    -0.49
    assigns
    -0.49
    POSITIVE LOGITS
     nahilalakip
    1.07
     similar
    1.06
     SIMILAR
    1.04
    RectangleBorder
    1.02
    Similar
    1.01
     Similar
    1.01
    similar
    1.00
    Похо
    0.97
    iliar
    0.92
     simil
    0.92
    Activations Density 0.175%

    No Known Activations