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. 14938
    Prev
    Next
    INDEX
    Explanations

    XML structure and data response elements

    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
     createSprite
    -0.91
     كومونز
    -0.89
     FormsModule
    -0.82
    mybatisplus
    -0.80
    astéro
    -0.80
    VERTISEMENT
    -0.79
     $_"
    -0.78
    ugeot
    -0.77
    AsUp
    -0.75
     FetchType
    -0.75
    POSITIVE LOGITS
    ↵↵
    2.31
    ↵↵↵
    1.70
    ↵
    1.67
    ↵↵↵↵
    1.65
    ↵↵↵↵↵
    1.54
    <h2>
    1.48
    ↵↵↵↵↵↵
    1.46
    <eos>
    1.39
    [toxicity=0]
    1.31
    ↵↵↵↵↵↵↵
    1.31
    Activations Density 1.029%

    No Known Activations