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. 5-GEMMASCOPE-RES-16K
    6. 3479
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating functionality and normal operation

    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
    şık
    -0.43
     necesariamente
    -0.41
     Tra
    -0.41
    setz
    -0.41
     le
    -0.40
    tieg
    -0.39
    árol
    -0.39
     ela
    -0.39
     عش
    -0.39
    rettet
    -0.38
    POSITIVE LOGITS
     snippetHide
    0.99
     undamaged
    0.97
     healthy
    0.95
     undisturbed
    0.91
     satisfactory
    0.89
     unharmed
    0.86
     flawless
    0.85
    正常
    0.84
     intact
    0.84
     satisfactorily
    0.82
    Activations Density 0.474%

    No Known Activations