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. 2-GEMMASCOPE-RES-16K
    6. 2192
    Prev
    Next
    INDEX
    Explanations

    instances of the word "this" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.75
     cdti
    -0.70
    AlterField
    -0.68
     autorytatywna
    -0.64
     للاسماء
    -0.63
     للمعارف
    -0.58
    Parcelize
    -0.57
    >>()
    -0.56
    protoimpl
    -0.55
     NKC
    -0.55
    POSITIVE LOGITS
     during
    0.77
     durante
    0.65
    during
    0.63
    ɵɵ
    0.60
     během
    0.58
     musim
    0.54
     DURING
    0.54
    flashdata
    0.53
     week
    0.53
    copg
    0.52
    Activations Density 0.402%

    No Known Activations