© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 3106
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and emotions

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

    "It was" or "It is"

    np_acts-logits-general · gemini-2.0-flash

    really positive evaluation

    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
    InputBorder
    -0.64
     PyObject
    -0.53
     незавершена
    -0.53
    ValueStyle
    -0.52
     gynhyrchwyd
    -0.52
    GOTREF
    -0.50
    主な
    -0.50
    不了
    -0.50
     quan
    -0.49
     JADX
    -0.48
    POSITIVE LOGITS
     really
    0.95
     veramente
    0.94
     verkligen
    0.92
    really
    0.91
     virkelig
    0.91
     Really
    0.90
     davvero
    0.90
    Really
    0.89
     vraiment
    0.88
     Truly
    0.88
    Activations Density 0.185%

    No Known Activations