© 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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 9462
    Prev
    Next
    INDEX
    Explanations

    emotional responses and struggles with self-control and disappointment

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

    following "to" indicating actions

    np_acts-logits-general · gemini-2.0-flash

    not to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.64
     ujednoznacz
    -0.55
    AsUp
    -0.55
    AddTagHelper
    -0.55
     “
    -0.53
    issements
    -0.48
     Sal
    -0.47
     T
    -0.47
    ("$.
    -0.46
    #
    -0.46
    POSITIVE LOGITS
     faſt
    0.76
     againſt
    0.69
     myſelf
    0.69
     immédi
    0.67
     ſta
    0.65
    脚注の使い方
    0.64
     ſtate
    0.64
     himſelf
    0.64
     dieß
    0.64
     diſt
    0.64
    Activations Density 0.125%

    No Known Activations