© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 9080
    Prev
    Next
    INDEX
    Explanations

    instances of possessive pronouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     myſelf
    -4.92
     itſelf
    -4.80
     Efq
    -4.56
     ―――――
    -4.49
     purpoſe
    -4.24
    ſelf
    -4.20
     Majefty
    -4.17
     Jefus
    -4.17
     Monfieur
    -4.14
     pleaſure
    -4.13
    POSITIVE LOGITS
     
    2.87
    ,
    2.73
    .
    2.59
     (
    2.50
    ↵
    2.36
    ↵↵
    2.31
    ’
    2.30
    <eos>
    2.30
     in
    2.18
     I
    2.17
    Activations Density 0.245%

    No Known Activations