© 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. 16-GEMMASCOPE-RES-16K
    11. 3446
    Prev
    Next
    INDEX
    Explanations

    discussions related to understanding and communication difficulties

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

    Followed by personal pronouns like "me" or "my"

    np_acts-logits-general · gemini-2.0-flash

    being told about me

    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
    给他们
    -0.57
    彼らは
    -0.53
     eles
    -0.51
     ihnen
    -0.49
     آنان
    -0.49
    stdc
    -0.49
     }}"></
    -0.48
     họ
    -0.48
     mereka
    -0.48
    urp
    -0.48
    POSITIVE LOGITS
     conmigo
    1.49
     comigo
    1.31
     me
    1.15
     my
    1.06
     conosco
    0.85
     моих
    0.85
    ándome
    0.84
     моего
    0.83
     mío
    0.83
    把我
    0.83
    Activations Density 0.435%

    No Known Activations