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. 18-GEMMASCOPE-RES-16K
    6. 14372
    Prev
    Next
    INDEX
    Explanations

    references to societal structures and implications of privilege

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, non-English words, or structural elements

    np_acts-logits-general · gemini-2.0-flash

    size, length, width or shear

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    这是一个
    -0.60
     là
    -0.55
     são
    -0.54
     является
    -0.53
    是个
    -0.49
    是一個
    -0.49
    เป็น
    -0.49
     είναι
    -0.48
     merupakan
    -0.48
     serem
    -0.47
    POSITIVE LOGITS
     nevertheless
    0.89
    twimg
    0.76
     nonetheless
    0.76
     HomeScreen
    0.75
    ConstraintMaker
    0.74
     deserve
    0.74
    SequentialGroup
    0.71
     useHistory
    0.70
     deserves
    0.70
     CURIAM
    0.68
    Activations Density 0.308%

    No Known Activations