© 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. 15-GEMMASCOPE-RES-16K
    11. 8949
    Prev
    Next
    INDEX
    Explanations

    frequency and context of prepositions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DebuggerNonUser
    -0.62
    enerys
    -0.58
    Precautionary
    -0.52
     propOrder
    -0.50
    ➌
    -0.50
    المكان
    -0.45
     brano
    -0.44
     Spani
    -0.43
    cautionary
    -0.43
    isine
    -0.43
    POSITIVE LOGITS
    AddTagHelper
    0.67
    inaldi
    0.66
    CloseOperation
    0.64
     HasFactory
    0.60
    abstractmethod
    0.60
     '{@
    0.58
    jsxFileName
    0.57
     تانيه
    0.56
     nakalista
    0.56
    __(/*!
    0.55
    Activations Density 0.421%

    No Known Activations