© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 7110
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic transactions and financial discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ModelSerializer
    -0.63
     esternos
    -0.41
    minecraftforge
    -0.40
     ExecuteAsync
    -0.39
     MainAxisSize
    -0.39
    AppMethodBeat
    -0.36
    PreAuthorize
    -0.35
     linkovi
    -0.35
    AnchorTagHelper
    -0.35
    GetAxis
    -0.35
    POSITIVE LOGITS
     thousands
    3.63
    thousands
    3.22
     hundreds
    3.17
     millions
    3.17
     Thousands
    3.14
    Thousands
    3.11
    hundreds
    2.80
    Hundreds
    2.78
     Hundreds
    2.77
    millions
    2.72
    Activations Density 1.357%

    No Known Activations