© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 5246
    Prev
    Next
    INDEX
    Explanations

    phrases related to access and control within systems or environments, particularly in regards to information or resources

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

    Tokens preceding "access"

    np_acts-logits-general · gemini-2.0-flash

    access

    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
    
    -0.60
     تانيه
    -0.58
     Himo
    -0.54
    ismet
    -0.52
    IPAC
    -0.51
    født
    -0.51
     CreateTagHelper
    -0.50
    blurRadius
    -0.49
    uterte
    -0.49
    StringCopy
    -0.48
    POSITIVE LOGITS
     access
    3.78
    access
    3.28
     Access
    3.10
    Access
    3.03
     ACCESS
    2.71
     accès
    2.71
     acceso
    2.70
     acesso
    2.67
     accessing
    2.53
    ACCESS
    2.53
    Activations Density 0.397%

    No Known Activations