© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 2508
    Prev
    Next
    INDEX
    Explanations

    references to historical contexts and origins

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "From the"

    np_acts-logits-general · gemini-2.0-flash

    phrases indicating origin or perspective

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rospy
    -0.51
    力は
    -0.44
    BufferException
    -0.43
    日は
    -0.43
     از
    -0.43
    曲は
    -0.40
    問題は
    -0.39
     chances
    -0.39
    が欲しい
    -0.39
    ність
    -0.39
    POSITIVE LOGITS
     standpoint
    1.77
     perspective
    1.48
     vantage
    1.30
     onwards
    1.21
    perspective
    1.18
     viewpoint
    1.15
     outset
    1.15
     perspectives
    1.07
     Perspective
    1.02
     PERSPECT
    1.01
    Activations Density 0.287%

    No Known Activations