© 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. 9-GEMMASCOPE-RES-16K
    11. 8076
    Prev
    Next
    INDEX
    Explanations

    assertions related to certainty and clarity in arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BeginContext
    -0.78
    tagHelperRunner
    -0.76
    🏻‍♀️
    -0.73
    enumii
    -0.73
     يتيمه
    -0.73
    TagHelper
    -0.72
    sidemargin
    -0.70
    ApiModel
    -0.69
    AutoScale
    -0.69
    ^(@)
    -0.68
    POSITIVE LOGITS
     unequivocal
    0.80
     unambiguous
    0.76
     unequivocally
    0.76
     certainty
    0.73
     clear
    0.73
     conclusively
    0.68
     definite
    0.65
     firmly
    0.65
     certitude
    0.64
     unanimous
    0.63
    Activations Density 0.725%

    No Known Activations