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. 17-GEMMASCOPE-RES-16K
    6. 6065
    Prev
    Next
    INDEX
    Explanations

    equality and inequality comparison operators in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ly
    -0.99
    性
    -0.88
    ので
    -0.79
    Agg
    -0.76
    choline
    -0.75
     comptes
    -0.75
     Pind
    -0.73
    ști
    -0.72
     lowa
    -0.71
     ....
    -0.71
    POSITIVE LOGITS
    ––––
    1.08
    ര്‍
    1.06
     ​​
    1.04
     –
    1.02
    ায়
    1.00
     
    0.96
    LOGGER
    0.94
    باً
    0.92
    راً
    0.91
    য়ে
    0.90
    Activations Density 0.201%

    No Known Activations