© 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-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 8823
    Prev
    Next
    INDEX
    Explanations

    conjunctions and elements of mathematical notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.68
    TargetException
    -0.66
     EconPapers
    -0.63
     kaarangay
    -0.60
    WriteTagHelper
    -0.58
    uxxxx
    -0.58
    Kjelder
    -0.57
    SharedCtor
    -0.57
     protoimpl
    -0.56
    expandindo
    -0.56
    POSITIVE LOGITS
     both
    0.40
    owohl
    0.38
     portions
    0.37
     or
    0.35
     either
    0.34
     Both
    0.32
     BOTH
    0.31
     beiden
    0.31
     ambos
    0.31
     two
    0.30
    Activations Density 1.048%

    No Known Activations