© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14869
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and statements that express uncertainty or hypotheticals

    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
    ſelves
    -1.00
     pleaſure
    -1.00
    ſelf
    -0.99
     itſelf
    -0.99
     ―――――
    -0.97
     Majefty
    -0.97
     myſelf
    -0.95
     Efq
    -0.90
     ་་
    -0.89
     Anſ
    -0.89
    POSITIVE LOGITS
     they
    1.62
     we
    1.39
     someone
    1.38
     somebody
    1.32
     you
    1.28
    someone
    1.21
    somebody
    1.13
     SOMEONE
    1.04
     people
    1.03
     nobody
    1.00
    Activations Density 0.505%

    No Known Activations