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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 4229
    Prev
    Next
    INDEX
    Explanations

    terms related to specific purposes, particularly in legal, financial, and academic contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     for
    -0.73
    #+#
    -0.60
    for
    -0.53
     untuk
    -0.52
    ással
    -0.49
    對於
    -0.47
    めでとう
    -0.44
     برای
    -0.44
     suficientes
    -0.43
    对于
    -0.43
    POSITIVE LOGITS
     purposes
    2.29
    purposes
    1.83
     Purposes
    1.73
     purpose
    1.55
     sake
    1.41
    purpose
    1.28
     Zwecke
    1.27
    Purpose
    1.27
     Purpose
    1.21
     PURPOSE
    1.16
    Activations Density 0.567%

    No Known Activations