© 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. 18-GEMMASCOPE-RES-16K
    11. 2621
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential risks and uncertainties related to clinical trials and product approvals

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

    followed by "to"

    np_acts-logits-general · gemini-2.0-flash

    states or actions followed by what's next

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Paglinawan
    -1.31
    Personendaten
    -1.27
     مرئيه
    -1.27
    OGND
    -1.26
    AccessorTable
    -1.21
     kaarangay
    -1.19
     مشين
    -1.19
    rungsseite
    -1.19
     myſelf
    -1.19
     AssemblyCulture
    -1.17
    POSITIVE LOGITS
     
    0.89
    ↵
    0.88
    .
    0.84
    ,
    0.82
    <strong>
    0.81
     also
    0.81
      
    0.81
     again
    0.78
    ↵↵
    0.77
     (
    0.77
    Activations Density 0.994%

    No Known Activations