Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 85709
    Prev
    Next
    INDEX
    Explanations

    references to legal and administrative processes related to benefits and claims

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

    benefits, denial, termination notices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
    ErrUnexpectedEOF
    -0.32
    paisaje
    -0.29
     وتسجيلات
    -0.29
     Wellen
    -0.28
     Mendes
    -0.27
    IModel
    -0.27
     Schön
    -0.27
     alm
    -0.26
    zionalità
    -0.26
     democrática
    -0.26
    POSITIVE LOGITS
    Harsh
    0.55
     GenerationType
    0.52
    iibo
    0.52
    ikusbot
    0.51
    transQ
    0.50
    :✨
    0.50
     larmes
    0.48
    最快更新
    0.47
     témoig
    0.47
    FieldDescriptor
    0.47
    Activations Density 0.113%

    No Known Activations