© 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. 8677
    Prev
    Next
    INDEX
    Explanations

    phrases that introduce uncertainty or conditional situations

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

    "Whether" followed by a clause

    np_acts-logits-general · gemini-2.0-flash

    Whether or not

    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
    WithIOException
    -1.07
    AndEndTag
    -0.96
    ſelf
    -0.92
     purpoſe
    -0.91
     Jefus
    -0.90
     pleaſure
    -0.89
     Monfieur
    -0.89
     houſe
    -0.89
     الحره
    -0.88
     raiſ
    -0.88
    POSITIVE LOGITS
     they
    0.96
     WHETHER
    0.92
     there
    0.88
     it
    0.85
     whether
    0.84
     we
    0.82
    whether
    0.82
     Whether
    0.79
    Whether
    0.79
     you
    0.77
    Activations Density 0.049%

    No Known Activations