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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 11867
    Prev
    Next
    INDEX
    Explanations

    technical formatting elements in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -1.00
     ModelExpression
    -0.91
     resourceCulture
    -0.89
    UnsafeEnabled
    -0.85
     Italijani
    -0.80
    qrstuvwxyz
    -0.80
    StoryboardSegue
    -0.80
    DeleteBehavior
    -0.78
    PerformLayout
    -0.77
    FieldBuilder
    -0.76
    POSITIVE LOGITS
    enumi
    1.11
    enumii
    0.76
    ValueStyle
    0.64
    BeginContext
    0.63
    Revenir
    0.60
    IMPORTED
    0.58
    сылкі
    0.57
    tagHelper
    0.55
    far
    0.51
     noten
    0.51
    Activations Density 0.476%

    No Known Activations