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. 2-GEMMASCOPE-RES-16K
    6. 6684
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences or feelings of the speaker

    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
    AddTagHelper
    -1.03
     @"/
    -0.94
     EconPapers
    -0.87
    ंदीखरीदारी
    -0.86
    tvguidetime
    -0.80
     MainAxisSize
    -0.79
    IntoConstraints
    -0.79
    Tikang
    -0.79
    WriteBarrier
    -0.78
     ModelExpression
    -0.78
    POSITIVE LOGITS
    brigens
    0.53
     acaso
    0.51
    uropa
    0.47
     نظر
    0.47
    ByUser
    0.46
     Umum
    0.43
    fortunately
    0.43
     IMO
    0.42
     akal
    0.41
     ears
    0.41
    Activations Density 0.227%

    No Known Activations