© 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. 24-GEMMASCOPE-RES-16K
    11. 2597
    Prev
    Next
    INDEX
    Explanations

    elements related to AWS IAM roles and policies

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

    AWS or Amazon services and resources

    np_acts-logits-general · gemini-2.0-flash

    Amazon AWS services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Disliked
    -0.66
    zeczy
    -0.63
    ScopeManager
    -0.61
     DialogResult
    -0.60
    omla
    -0.59
    viewDidLoad
    -0.58
    othek
    -0.57
     Danilo
    -0.55
     Erasmus
    -0.55
    versace
    -0.55
    POSITIVE LOGITS
     Amazon
    0.98
    Amazon
    0.86
     Prime
    0.74
     AWS
    0.73
     amazon
    0.73
    amazonaws
    0.70
    mazon
    0.68
     AMAZON
    0.67
    Prime
    0.67
    AWS
    0.66
    Activations Density 0.276%

    No Known Activations