© 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. 12731
    Prev
    Next
    INDEX
    Explanations

    sentences expressing subjective opinions or emotions

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

    Following "is" or similar verbs

    np_acts-logits-general · gemini-2.0-flash

    interesting and unusual observations

    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
    جغرافيا
    -0.59
    ConstraintMaker
    -0.50
    bedingt
    -0.50
    ide
    -0.48
     مُعرِّف
    -0.47
    سطس
    -0.46
     antemano
    -0.46
     enfermed
    -0.46
    ambilan
    -0.45
    nellement
    -0.44
    POSITIVE LOGITS
     interesting
    1.78
     surprising
    1.56
     fascinating
    1.55
     remarkable
    1.53
     strange
    1.50
    interesting
    1.48
     amusing
    1.48
     intriguing
    1.45
     curious
    1.45
     ironic
    1.43
    Activations Density 0.455%

    No Known Activations