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. 8-GEMMASCOPE-RES-16K
    6. 5985
    Prev
    Next
    INDEX
    Explanations

    structured data or code elements in programming or technical documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.63
    ToScroll
    -0.60
    —.
    -0.56
     Besøkt
    -0.56
    ,:,
    -0.55
     CanadaChoose
    -0.55
    atts
    -0.55
     ||
    
    -0.55
    umsy
    -0.54
     another
    -0.54
    POSITIVE LOGITS
    ècie
    0.70
     الرياضيه
    0.69
    ⓧ
    0.66
     Turkmenistan
    0.55
     rendel
    0.53
     refusé
    0.53
     grail
    0.52
    UnsafeEnabled
    0.52
    Azerbaijan
    0.51
    cyjna
    0.50
    Activations Density 0.704%

    No Known Activations