© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 9311
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and terms related to formal definitions or methodologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/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.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     XNUMX
    -0.71
    󠁣
    -0.66
    !*\
    -0.66
    Clik
    -0.64
    Datuak
    -0.64
     שוליים
    -0.63
     otomatig
    -0.63
     disambiguazione
    -0.63
     ujednoznacz
    -0.63
    __*/
    -0.61
    POSITIVE LOGITS
    idać
    0.57
     sanitarias
    0.56
     corresponding
    0.55
     Tunisie
    0.52
     comparaison
    0.52
     flotante
    0.52
     corresponded
    0.51
     industriales
    0.50
     correspondiente
    0.49
     observed
    0.49
    Activations Density 12.735%

    No Known Activations