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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 6442
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual named Hal

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.83
    AddTagHelper
    -0.73
    styleType
    -0.68
    typeorm
    -0.66
    IVEREF
    -0.60
     "..\..\..\
    -0.60
    Ikr
    -0.59
    はじめに
    -0.59
    Rüyada
    -0.59
     sube
    -0.58
    POSITIVE LOGITS
     Hal
    0.74
    hal
    0.69
    Hal
    0.68
     engines
    0.65
     engine
    0.64
     Quick
    0.63
    Quick
    0.61
     Engine
    0.61
     HAL
    0.59
    getBlock
    0.58
    Activations Density 0.130%

    No Known Activations