© 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. 4-GEMMASCOPE-RES-16K
    11. 3313
    Prev
    Next
    INDEX
    Explanations

    references to different parts of narratives or stories, specifically the beginning, middle, and end

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     بيها
    -0.75
    WriteBarrier
    -0.71
    @[+][
    -0.69
    ględ
    -0.66
    autogui
    -0.62
    ウンジ
    -0.59
    GenerationType
    -0.59
    ágeno
    -0.58
     مرئيه
    -0.57
    imentel
    -0.57
    POSITIVE LOGITS
     opening
    0.90
     start
    0.88
     beginning
    0.85
    beginning
    0.84
     começo
    0.84
     onset
    0.82
     getStart
    0.80
    opening
    0.79
     Opening
    0.79
     beginnings
    0.79
    Activations Density 0.207%

    No Known Activations