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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 114510
    Prev
    Next
    INDEX
    Explanations

    patterns and frequencies in scientific measurements or observations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ReusableCell
    -0.79
    IUrlHelper
    -0.71
    BagLayout
    -0.70
    extAlignment
    -0.68
     ProtoMessage
    -0.67
    Parcelize
    -0.66
    ManagedBean
    -0.65
     BaseActivity
    -0.61
     Normdatei
    -0.59
    ArgsConstructor
    -0.59
    POSITIVE LOGITS
     bæ
    0.32
    ↵↵
    0.32
     this
    0.31
     зді
    0.30
     Bedeutung
    0.29
    ity
    0.28
    这
    0.28
    <strong>
    0.27
     yö
    0.27
    räck
    0.27
    Activations Density 0.128%

    No Known Activations