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-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11838
    Prev
    Next
    INDEX
    Explanations

    terms related to evaporation and phase changes in liquids

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Illuminate
    -0.34
    SizeMode
    -0.31
    fontein
    -0.31
    спери
    -0.30
    adins
    -0.30
    #+#
    -0.30
    bruk
    -0.29
    ทาง
    -0.29
     estrenar
    -0.29
     acidosis
    -0.29
    POSITIVE LOGITS
     autorytatywna
    0.91
     CURIAM
    0.65
    Evaporation
    0.64
     evaporation
    0.63
     виправивши
    0.60
    CloseOperation
    0.59
    ValueStyle
    0.57
    IndentedString
    0.57
     للاسماء
    0.57
    expandindo
    0.57
    Activations Density 0.395%

    No Known Activations