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. 14511
    Prev
    Next
    INDEX
    Explanations

    references to metal materials in various contexts

    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
    PageFactory
    -0.82
     niacin
    -0.80
     myrtle
    -0.78
    sunshine
    -0.78
    قایناق‌لار
    -0.77
     eccell
    -0.77
     SAGE
    -0.76
    adaptiveStyles
    -0.75
    BufferException
    -0.75
    visiae
    -0.75
    POSITIVE LOGITS
     metal
    2.17
    metal
    2.11
     Metal
    2.10
    Metal
    2.00
     METAL
    1.99
    METAL
    1.89
     metals
    1.68
    metals
    1.53
     Metals
    1.51
     métal
    1.51
    Activations Density 0.067%

    No Known Activations