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. 25-GEMMASCOPE-RES-16K
    6. 4327
    Prev
    Next
    INDEX
    Explanations

    transitional phrases that indicate a change in thought or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.81
    دانشنامهٔ
    -0.80
    RegistryLite
    -0.72
     ويكيپيديا
    -0.72
    principalColumn
    -0.71
    Билгалдахарш
    -0.67
    ]-'
    -0.67
    #+#
    -0.65
    titleMargin
    -0.65
    []>(
    -0.64
    POSITIVE LOGITS
     then
    0.79
    ,
    0.72
     wait
    0.72
    !
    0.69
     while
    0.62
     what
    0.62
     why
    0.61
     where
    0.61
     alors
    0.58
     puis
    0.58
    Activations Density 0.122%

    No Known Activations