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. 16-GEMMASCOPE-RES-16K
    6. 4436
    Prev
    Next
    INDEX
    Explanations

    patterns of contrast and variation

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

    "Some" followed by "while" or "others"

    np_acts-logits-general · gemini-2.0-flash

    some while others

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InitStruct
    -0.62
    gdx
    -0.58
    MergeFrom
    -0.54
    AutoresizingMask
    -0.53
    śnie
    -0.52
     Мексичка
    -0.50
    weetened
    -0.48
    bootstrapcdn
    -0.48
    География
    -0.48
    嘧
    -0.47
    POSITIVE LOGITS
     others
    1.68
    Others
    1.54
     Others
    1.48
    others
    1.46
     OTHERS
    1.22
     البعض
    0.91
     some
    0.88
    OTHERS
    0.86
     certains
    0.83
     sometimes
    0.83
    Activations Density 0.324%

    No Known Activations