© 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. 6826
    Prev
    Next
    INDEX
    Explanations

    phrases advocating for understanding and giving others the benefit of the doubt

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

    "Give" and related words

    np_acts-logits-general · gemini-2.0-flash

    give the benefit of the doubt

    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
     Référence
    -0.61
    InitStruct
    -0.58
     noDo
    -0.57
     Masson
    -0.55
    MathML
    -0.54
    TagHelper
    -0.53
     Regu
    -0.52
    UnknownFieldSet
    -0.52
    DispatchToProps
    -0.51
     doGet
    -0.50
    POSITIVE LOGITS
     forgiving
    0.76
     forgive
    0.65
     give
    0.62
     forgiveness
    0.62
    give
    0.58
     Give
    0.55
    原谅
    0.55
    Give
    0.55
     fair
    0.54
     forgiven
    0.54
    Activations Density 0.347%

    No Known Activations