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. 7-GEMMASCOPE-RES-16K
    6. 9470
    Prev
    Next
    INDEX
    Explanations

    references to access, particularly in relation to healthcare, financial resources, and essential services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     venido
    -0.53
    ↵
    -0.48
     stí
    -0.46
    ResumeLayout
    -0.44
    wpdb
    -0.44
    '
    -0.43
     primeiros
    -0.43
     declarado
    -0.43
     folgte
    -0.43
    こい
    -0.42
    POSITIVE LOGITS
     access
    1.70
     accessible
    1.56
     Access
    1.46
    access
    1.43
    accessible
    1.42
     accessing
    1.41
     ACCESS
    1.41
     accesses
    1.39
     Accessible
    1.33
    Access
    1.32
    Activations Density 0.192%

    No Known Activations