Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12-GEMMASCOPE-RES-16K
    6. 6360
    Prev
    Next
    INDEX
    Explanations

    phrases related to healthcare initiatives and social improvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TestBed
    -0.50
     TestBed
    -0.49
     jól
    -0.48
    Identyfik
    -0.46
     ok
    -0.45
    andina
    -0.44
    etes
    -0.43
     Superhost
    -0.43
    bereitung
    -0.43
     surviving
    -0.42
    POSITIVE LOGITS
    esserung
    0.82
     improvement
    0.78
    Portail
    0.72
     forbed
    0.68
    improvement
    0.68
    
    0.67
     transformation
    0.67
     réduction
    0.66
    improve
    0.65
     improvements
    0.63
    Activations Density 0.226%

    No Known Activations