© 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. 23-GEMMASCOPE-RES-16K
    6. 6081
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical concepts of estimation and emphasis on robustness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    
    -0.74
    TagMode
    -0.72
    cipar
    -0.64
     BoxDecoration
    -0.62
     consultato
    -0.61
    — 
    -0.60
     <=",
    -0.60
    __':
    -0.59
    hoppers
    -0.59
    الإنجليزية
    -0.58
    POSITIVE LOGITS
    e
    0.63
    ̯
    0.62
    ni
    0.52
    ng
    0.52
    cou
    0.51
    bou
    0.49
     dejes
    0.48
    jou
    0.47
    lt
    0.47
    mou
    0.47
    Activations Density 0.169%

    No Known Activations