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. 5887
    Prev
    Next
    INDEX
    Explanations

    various types of data structures and formatting in programming code

    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
     riuscito
    -0.75
     andato
    -0.63
    رشف
    -0.62
     quæ
    -0.60
    OGND
    -0.60
     Ranks
    -0.59
    MemoryWarning
    -0.59
     resourceCulture
    -0.59
     pages
    -0.59
     villages
    -0.59
    POSITIVE LOGITS
    acids
    0.45
    exels
    0.45
    juries
    0.43
    arities
    0.42
    ogens
    0.41
    clays
    0.41
    rois
    0.41
    stuffs
    0.40
    gels
    0.40
    WriteTagHelper
    0.40
    Activations Density 0.908%

    No Known Activations