© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 8962
    Prev
    Next
    INDEX
    Explanations

    references to fraudulent activities related to identity and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +:+
    -0.48
    LookAnd
    -0.48
    الحياه
    -0.42
     ✭✭
    -0.42
    adaptiveStyles
    -0.40
    +#+#
    -0.39
     Spitze
    -0.36
    richTextPanel
    -0.35
    XmlAccessorType
    -0.33
    DIPSETTING
    -0.32
    POSITIVE LOGITS
     passport
    1.11
     passports
    1.09
     identity
    1.06
     ID
    1.05
     identification
    1.05
     certificates
    1.05
     IDs
    1.03
     documents
    1.02
     proof
    1.02
     certificate
    1.01
    Activations Density 0.454%

    No Known Activations