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. 20-GEMMASCOPE-RES-16K
    6. 11681
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a sequence or requirement

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

    "order to" phrase

    np_acts-logits-general · gemini-2.0-flash

    in order to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ProtoMessage
    -0.93
    MessageTagHelper
    -0.85
     MessageBoxIcon
    -0.79
    ]")]
    -0.78
    StructEnd
    -0.75
     fieldNum
    -0.74
     MainAxisSize
    -0.74
     Taktlose
    -0.73
     pleaſure
    -0.72
     AssemblyCulture
    -0.72
    POSITIVE LOGITS
     to
    0.68
    Để
    0.53
     Afin
    0.52
    Afin
    0.51
     successfully
    0.47
     word
    0.47
     words
    0.47
     ensuring
    0.47
     not
    0.46
     enabling
    0.44
    Activations Density 0.066%

    No Known Activations