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. 22-GEMMASCOPE-RES-16K
    6. 10969
    Prev
    Next
    INDEX
    Explanations

    concepts related to nature and the natural environment

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

    "nature"

    np_acts-logits-general · gemini-2.0-flash

    nature of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.84
     تضيفلها
    -0.83
    AddTagHelper
    -0.81
     pleaſure
    -0.80
     Monfieur
    -0.78
    SourceChecksum
    -0.72
    ftagPool
    -0.70
     naselje
    -0.69
     ***!
    -0.69
    ✨:
    -0.69
    POSITIVE LOGITS
     Nature
    0.71
     morte
    0.69
     NATURE
    0.67
    dly
    0.63
    Nature
    0.61
     mortes
    0.55
    d
    0.52
     nó
    0.52
     misma
    0.52
     nature
    0.52
    Activations Density 0.071%

    No Known Activations