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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13617
    Prev
    Next
    INDEX
    Explanations

    specific details related to forms and applications, especially regarding signatures and addresses

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

    Followed by numbers or instructions

    np_acts-logits-general · gemini-2.0-flash

    indicate details or status

    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
     الحره
    -0.56
    !*\
    -0.56
    arXiv
    -0.55
    άζ
    -0.55
     للاسماء
    -0.48
    TabLayout
    -0.46
     发表于
    -0.46
    newswire
    -0.46
    GeoNames
    -0.46
    wijl
    -0.44
    POSITIVE LOGITS
     Describe
    0.80
    describe
    0.79
     Briefly
    0.78
    Describe
    0.78
     brief
    0.77
     description
    0.77
    Brief
    0.77
     describe
    0.76
     details
    0.76
     please
    0.74
    Activations Density 0.277%

    No Known Activations