© 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. 3512
    Prev
    Next
    INDEX
    Explanations

    expressions of personal experiences and interactions within a group context

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

    Sentences starting with "We" or "I" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    we experienced things

    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
     annan
    -0.60
     devenus
    -0.56
    BeginContext
    -0.55
     milliers
    -0.55
    ক্ষ
    -0.52
     anciens
    -0.52
     siècles
    -0.51
     Polisi
    -0.50
    帖最后由
    -0.49
     dapur
    -0.48
    POSITIVE LOGITS
     booked
    0.85
     ordered
    0.74
     LOVED
    0.72
    WriteTagHelper
    0.69
     loved
    0.69
     dined
    0.69
    AndEndTag
    0.69
     chofe
    0.68
    complexContent
    0.63
     ordering
    0.62
    Activations Density 0.079%

    No Known Activations