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. 13-GEMMASCOPE-RES-16K
    6. 43
    Prev
    Next
    INDEX
    Explanations

    special formatting elements or symbols frequently used in technical or mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    technical or scientific terminology and data points within various contexts.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sp
    -0.42
    hod
    -0.42
    sp
    -0.38
    ho
    -0.38
    yorsunuz
    -0.38
    ke
    -0.38
     st
    -0.37
    ātu
    -0.36
    }>{
    -0.35
    ga
    -0.34
    POSITIVE LOGITS
    UrlResolution
    1.17
     kasarigan
    1.16
    MigrationBuilder
    1.10
    expandindo
    1.09
     Мексичка
    1.08
    GEBURTSDATUM
    1.08
     <=",
    1.07
    setVerticalGroup
    1.07
     CreateTagHelper
    1.06
    ftagPool
    1.06
    Activations Density 0.364%

    No Known Activations