© 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. 2-GEMMASCOPE-RES-16K
    11. 6906
    Prev
    Next
    INDEX
    Explanations

    the presence of zeros and numerical values in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -0.95
    dafx
    -0.94
    DockStyle
    -0.93
     Monfieur
    -0.93
     Jefus
    -0.92
     reaſon
    -0.91
    
    -0.90
    ^(@)
    -0.89
     itſelf
    -0.88
     Anſ
    -0.83
    POSITIVE LOGITS
    </blockquote>
    0.67
    doi
    0.59
      
    0.53
    ni
    0.52
     tek
    0.51
     https
    0.51
     http
    0.51
    те
    0.51
    ?
    0.50
    acaktır
    0.50
    Activations Density 0.232%

    No Known Activations