© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 8667
    Prev
    Next
    INDEX
    Explanations

    conditional statements and intricacies in logical structures

    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
     Administrativna
    -0.76
     GenerationType
    -0.68
    HasAnnotation
    -0.63
    AndEndTag
    -0.62
    OGND
    -0.59
    хьтан
    -0.59
    SequentialGroup
    -0.58
    الحياه
    -0.57
    __*/
    -0.56
    BeginContext
    -0.55
    POSITIVE LOGITS
     neither
    0.46
     tampoco
    0.45
     Tampoco
    0.44
     nobody
    0.43
     nor
    0.41
     eikä
    0.38
     nessun
    0.36
     vapa
    0.36
     koska
    0.36
     Neither
    0.36
    Activations Density 1.183%

    No Known Activations