© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 14397
    Prev
    Next
    INDEX
    Explanations

    terms related to gaining or increasing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BitmapFactory
    -0.45
     Responsible
    -0.44
     responsible
    -0.44
    contentLoaded
    -0.43
     surla
    -0.43
    drawSprites
    -0.43
    responsible
    -0.43
     incin
    -0.41
    Responsible
    -0.40
     patiently
    -0.40
    POSITIVE LOGITS
     gained
    2.61
     gain
    2.55
     gaining
    2.53
    gain
    2.44
     Gain
    2.42
    Gain
    2.36
     gains
    2.09
     GAIN
    2.05
     Gains
    1.81
    GAIN
    1.80
    Activations Density 0.084%

    No Known Activations