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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5743
    Prev
    Next
    INDEX
    Explanations

    information about system validity and operational procedures

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

    Follows "be" or a form of "be"

    np_acts-logits-general · gemini-2.0-flash

    states and qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     berbahaya
    -0.47
     meia
    -0.47
    ほうがいい
    -0.44
     mož
    -0.44
    Probable
    -0.43
    方がいい
    -0.43
    Dangerous
    -0.42
     appelés
    -0.42
     învă
    -0.41
    živ
    -0.40
    POSITIVE LOGITS
     חיצוניים
    0.86
    "])
    
    0.79
    '))
    
    0.76
    }")
    
    0.74
    AddHtmlAttribute
    0.73
    Complaint
    0.72
    下载附件
    0.71
     compliant
    0.71
    "]);
    
    0.71
    '])->
    0.71
    Activations Density 0.579%

    No Known Activations