© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 3226
    Prev
    Next
    INDEX
    Explanations

    words related to legal verdicts of guilt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lang
    -0.44
    aneous
    -0.40
     Professional
    -0.38
     mat
    -0.38
     professionals
    -0.36
     Company
    -0.35
     lang
    -0.35
     Internation
    -0.34
    ない
    -0.34
     vit
    -0.34
    POSITIVE LOGITS
     loyalty
    0.78
    loyalty
    0.74
     loyal
    0.70
    
    0.69
    loyal
    0.69
    Loyalty
    0.68
     guilty
    0.68
    guilty
    0.66
     library
    0.65
    toler
    0.65
    Activations Density 0.214%

    No Known Activations