© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 3357
    Prev
    Next
    INDEX
    Explanations

    references to notes or annotations in a document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vanjske
    -0.62
     estekak
    -0.62
    Grüße
    -0.58
     Kurz
    -0.55
    Jäh
    -0.55
    
    -0.55
    saraba
    -0.54
    savevideobot
    -0.53
    aughey
    -0.53
    ]<<"
    -0.53
    POSITIVE LOGITS
     note
    1.13
    Note
    1.10
     Note
    1.08
     NOTE
    1.07
    NOTE
    1.03
    note
    0.95
     Nota
    0.90
    Nota
    0.81
    notes
    0.76
     nota
    0.75
    Activations Density 0.227%

    No Known Activations