© 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. 7-GEMMASCOPE-RES-16K
    11. 14874
    Prev
    Next
    INDEX
    Explanations

    expectations and forecasts related to business or financial performance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    transQ
    -0.54
     getRule
    -0.49
     pravi
    -0.46
     prévention
    -0.46
     nacionalidad
    -0.45
    AddTagHelper
    -0.44
     autorytatywna
    -0.43
    ColumnIndex
    -0.43
    emballage
    -0.42
    piración
    -0.42
    POSITIVE LOGITS
     expected
    0.66
     likely
    0.63
     vora
    0.61
    likely
    0.58
     estimated
    0.55
    expected
    0.55
     Likely
    0.55
     anticipated
    0.55
     Expected
    0.54
     dürfte
    0.52
    Activations Density 0.219%

    No Known Activations