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. 25-GEMMASCOPE-RES-16K
    6. 5766
    Prev
    Next
    INDEX
    Explanations

    programming-related terms, specifically related to data structure manipulations like 'set', 'get', and 'trim'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     (?)
    -0.53
     Laird
    -0.52
    ?).
    -0.52
     będziesz
    -0.51
     Paglinawan
    -0.51
     Yol
    -0.50
     Otero
    -0.50
    isian
    -0.49
    öy
    -0.49
    hésite
    -0.48
    POSITIVE LOGITS
    ViewFeatures
    0.62
    CGRectMake
    0.62
    IsContent
    0.61
    XmlAccessType
    0.61
     CreateTagHelper
    0.59
    AnchorStyles
    0.55
    autoIncrement
    0.53
    SaveChangesAsync
    0.52
    (&:
    0.52
    };
    0.51
    Activations Density 0.061%

    No Known Activations