© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 8236
    Prev
    Next
    INDEX
    Explanations

    emotional expressions related to feelings and perceptions

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

    that can be relative pronouns or possessive adjectives

    np_acts-logits-general · gemini-2.0-flash

    who or whom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsMutable
    -1.03
    DoubleQuotes
    -0.98
     виправивши
    -0.88
    sidemargin
    -0.85
    TypedDataSet
    -0.84
    several
    -0.84
    BeginInit
    -0.84
    PerformLayout
    -0.84
     several
    -0.82
    parsedMessage
    -0.82
    POSITIVE LOGITS
     who
    0.66
     whom
    0.64
     którzy
    0.63
     their
    0.62
     kteří
    0.61
     or
    0.53
     themselves
    0.49
    whom
    0.48
    或者
    0.46
     THEIR
    0.46
    Activations Density 0.459%

    No Known Activations