© 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. 37-GEMMASCOPE-RES-16K
    6. 3942
    Prev
    Next
    INDEX
    Explanations

    references to individuals involved in financial discussions or assistance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     organisation
    -0.57
     organisations
    -0.48
     organisational
    -0.45
    organisation
    -0.44
     realisation
    -0.43
    +#+#
    -0.42
     recognise
    -0.41
     recognised
    -0.41
     realising
    -0.40
     recognises
    -0.39
    POSITIVE LOGITS
     Infórmanos
    0.71
    IsPostBack
    0.59
    StoryboardSegue
    0.57
     mijne
    0.55
     Wiktionnaire
    0.55
    الحياه
    0.54
     Pardavimas
    0.53
    arangay
    0.53
     autorytatywna
    0.51
     TextInputType
    0.51
    Activations Density 0.179%

    No Known Activations