© 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-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 5748
    Prev
    Next
    INDEX
    Explanations

    terms related to various types of risk

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bersi
    -0.54
     årene
    -0.53
     particolare
    -0.53
     geçti
    -0.52
     mẽ
    -0.50
     lavorato
    -0.50
     battre
    -0.49
    Served
    -0.48
     particolari
    -0.47
     Toilette
    -0.47
    POSITIVE LOGITS
     risk
    4.54
     Risk
    4.16
    risk
    4.01
    Risk
    3.99
     risks
    3.86
     RISK
    3.79
     Risks
    3.47
    RISK
    3.44
    risks
    3.21
    Risks
    3.10
    Activations Density 0.082%

    No Known Activations