© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 4096
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens after "Let" followed by an assignment

    np_acts-logits-general · gemini-2.0-flash

    calculate mathematical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lético
    -0.45
     geologic
    -0.44
     dramatically
    -0.44
     referenced
    -0.43
    nullptr
    -0.42
    referenced
    -0.41
    ?!?
    -0.40
     overwhelm
    -0.40
     critters
    -0.39
     totaled
    -0.39
    POSITIVE LOGITS
    ՚
    0.68
    upto
    0.65
     препратки
    0.63
    Contd
    0.61
     upto
    0.59
    
    0.57
    __":
    
    0.57
     :-
    0.54
     Italijanski
    0.53
     NCERT
    0.52
    Activations Density 0.236%

    No Known Activations