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. 7999
    Prev
    Next
    INDEX
    Explanations

    arguments advocating for contraceptive use in movies and discussions about sexual health

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

    debate or reasoning

    np_acts-logits-general · gemini-2.0-flash

    ethical and logical arguments

    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
    CodeAttribute
    -0.67
     Meksiku
    -0.63
    dotenv
    -0.62
    urlpatterns
    -0.58
     IService
    -0.58
    εύ
    -0.56
    Tikang
    -0.55
    StreetMap
    -0.55
     melaporkan
    -0.54
     WebApplication
    -0.53
    POSITIVE LOGITS
     arguments
    2.49
     argument
    2.44
     Arguments
    2.15
     Argument
    2.10
    arguments
    2.04
    argument
    1.99
     argumento
    1.97
    Argument
    1.97
     argue
    1.94
     argumentos
    1.92
    Activations Density 0.834%

    No Known Activations