© 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. 21-GEMMASCOPE-RES-16K
    11. 1152
    Prev
    Next
    INDEX
    Explanations

    the first-person perspective in the text, focusing on occurrences of "I" and related phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atoto
    -0.50
     CreateTagHelper
    -0.46
    ordu
    -0.45
    klare
    -0.44
    phan
    -0.44
    hend
    -0.43
    MLLoader
    -0.43
    StoreMessageInfo
    -0.42
    Searching
    -0.41
    RegistryLite
    -0.41
    POSITIVE LOGITS
     sure
    1.58
     doubt
    1.38
     bet
    1.34
    sure
    1.33
     imagine
    1.27
     SURE
    1.23
     suspect
    1.21
    doubt
    1.18
     guessing
    1.18
     certeza
    1.17
    Activations Density 0.266%

    No Known Activations