© 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. 3-GEMMASCOPE-RES-16K
    6. 1807
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and operators in a formal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     iſt
    -1.20
     ―――――
    -1.08
     itſelf
    -1.07
     myſelf
    -0.98
     faſt
    -0.96
     Theſe
    -0.95
    ſelf
    -0.95
     ་་
    -0.94
     themſelves
    -0.92
     Beſ
    -0.91
    POSITIVE LOGITS
     \
    1.13
    \
    0.89
     /\.
    0.75
    ;\
    0.70
    >\
    0.64
    assadors
    0.64
    )\
    0.63
    {\
    0.63
     \&
    0.63
     jurídica
    0.63
    Activations Density 0.435%

    No Known Activations