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. 13486
    Prev
    Next
    INDEX
    Explanations

    commands and actions commonly associated with scripting or programming

    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
     Majefty
    -0.95
     pleaſure
    -0.95
     myſelf
    -0.90
     Houſe
    -0.88
     preſent
    -0.85
     ſeveral
    -0.85
     Reſ
    -0.84
     uſed
    -0.83
     ſever
    -0.82
     Conſ
    -0.82
    POSITIVE LOGITS
     grep
    0.64
    grep
    0.63
    ApiModelProperty
    0.62
     awk
    0.61
    tagHelper
    0.57
     MotionEvent
    0.56
    git
    0.55
    rm
    0.55
    unicorn
    0.54
     sed
    0.54
    Activations Density 0.161%

    No Known Activations