Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8182
    Prev
    Next
    INDEX
    Explanations

    repeated references to 'thing,' 'man,' and 'people' indicating discussions about experiences or concepts around humanity and relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     todo
    -0.50
    uanya
    -0.48
     strictly
    -0.45
     added
    -0.45
     a
    -0.43
    という
    -0.43
     overall
    -0.42
    良
    -0.42
     may
    -0.42
    ’
    -0.42
    POSITIVE LOGITS
     للمعارف
    1.07
    elemField
    0.89
     useAppContext
    0.86
    onAttach
    0.85
    postsleuth
    0.82
    GeneratedValue
    0.81
     חיצוניים
    0.81
     pinulongan
    0.80
     whoever
    0.79
    RenderAtEndOf
    0.79
    Activations Density 0.228%

    No Known Activations