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. 21-GEMMASCOPE-RES-16K
    6. 7043
    Prev
    Next
    INDEX
    Explanations

    technical terminology and keywords related to programming and software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    -1.09
    ,
    -1.07
     
    -0.98
     (
    -0.95
    /
    -0.91
    (
    -0.88
    -
    -0.88
    :
    -0.86
    ’
    -0.83
     and
    -0.83
    POSITIVE LOGITS
     myſelf
    1.68
     Савезне
    1.66
    LookAnd
    1.66
     houſe
    1.66
     pleaſure
    1.65
     Houſe
    1.58
     Roskov
    1.56
     ſtate
    1.56
     purpoſe
    1.55
    ंदीखरीदारी
    1.55
    Activations Density 0.797%

    No Known Activations