© 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. 3917
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss the concepts of responsibility and identity within dialogues

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

    Question words (who, what, which, where, whom)

    np_acts-logits-general · gemini-2.0-flash

    who or which selection

    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
    ItemBackground
    -0.57
     consultato
    -0.56
     idolatry
    -0.53
    mergeFrom
    -0.52
    onsored
    -0.48
    nessione
    -0.48
    =#{
    -0.48
    loon
    -0.47
     Heber
    -0.47
     _$
    -0.47
    POSITIVE LOGITS
     each
    0.78
    บ้าง
    0.64
    哪些
    0.63
     कौन
    0.63
     صوتيه
    0.60
    each
    0.57
     nhiêu
    0.57
     کدام
    0.56
     nào
    0.56
     poszczegól
    0.55
    Activations Density 0.241%

    No Known Activations