© 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. 10649
    Prev
    Next
    INDEX
    Explanations

    references to individuals named "Robert."

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

    "Robert" followed by names/surnames

    np_acts-logits-general · gemini-2.0-flash

    Robert and surnames

    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
     GenerationType
    -0.94
    ſelves
    -0.72
     purpoſe
    -0.69
     greateſt
    -0.68
     pleaſure
    -0.68
     Italijanski
    -0.67
    HasAnnotation
    -0.66
     reaſon
    -0.66
    ſelf
    -0.65
     fevere
    -0.64
    POSITIVE LOGITS
    bie
    0.67
    Manbalar
    0.53
    bi
    0.52
     Bob
    0.49
    ble
    0.49
    би
    0.47
    ました
    0.44
    Bob
    0.44
    泊
    0.44
    oward
    0.44
    Activations Density 0.091%

    No Known Activations