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. 5-GEMMASCOPE-RES-16K
    6. 14574
    Prev
    Next
    INDEX
    Explanations

    elements related to scientific research and experimental findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Савезне
    -1.20
    writeFieldEnd
    -1.15
    tagHelperRunner
    -1.10
    ⓧ
    -1.08
    SourceChecksum
    -1.05
    principalTable
    -1.01
    EndGlobalSection
    -0.99
     '\\;'
    -0.96
     Chwiliwch
    -0.95
    SequentialGroup
    -0.95
    POSITIVE LOGITS
    </strong>
    0.79
    </em>
    0.77
    </u>
    0.74
    </b>
    0.73
    </i>
    0.72
    ”
    0.59
    "
    0.57
     [
    0.55
    [
    0.51
    </h5>
    0.51
    Activations Density 0.126%

    No Known Activations