© 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. 20-GEMMASCOPE-RES-16K
    11. 11381
    Prev
    Next
    INDEX
    Explanations

    phrases related to access and availability of information or resources

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

    preceding or related to "access"

    np_acts-logits-general · gemini-2.0-flash

    giving or gaining access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.73
     CreateTagHelper
    -0.70
     تانيه
    -0.68
     Вікі
    -0.64
     intStringLen
    -0.64
    ItemBackground
    -0.60
    ismet
    -0.59
    IPAC
    -0.59
    født
    -0.57
    ScopeManager
    -0.56
    POSITIVE LOGITS
     access
    3.13
    access
    2.63
     Access
    2.43
    Access
    2.41
     acceso
    2.28
     acesso
    2.26
     accès
    2.21
     ACCESS
    2.15
     accesses
    2.02
     accessing
    2.02
    Activations Density 0.399%

    No Known Activations