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. 1874
    Prev
    Next
    INDEX
    Explanations

    technical or scientific terminology related to processes and measurements

    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
    SSA
    -0.80
    CSR
    -0.79
    SSR
    -0.79
    CCS
    -0.78
    AMS
    -0.77
    SDF
    -0.77
    PPP
    -0.77
    TSA
    -0.76
    PCP
    -0.76
    SA
    -0.76
    POSITIVE LOGITS
    HomeAsUpEnabled
    0.71
     IBRARY
    0.67
    ंदीखरीदारी
    0.67
    #+#
    0.66
    InjectMocks
    0.65
     AssemblyTitle
    0.65
     Normdatei
    0.64
    BRARY
    0.63
     AssemblyCulture
    0.63
     AssemblyCompany
    0.62
    Activations Density 1.055%

    No Known Activations