© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15387
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant actions or events involving individuals or groups

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

    Tokens preceding certain verbs or states of being

    np_acts-logits-general · gemini-2.0-flash

    respectively

    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
    AutoScaleMode
    -0.75
     모든
    -0.72
     Sociales
    -0.65
    #+#
    -0.64
     utafitiHapana
    -0.64
    expandindo
    -0.63
     négociations
    -0.61
    所有的
    -0.60
     dépens
    -0.60
     ostavi
    -0.60
    POSITIVE LOGITS
     respectively
    2.13
     respective
    2.01
    respectively
    1.92
    それぞれ
    1.66
    各自
    1.59
     masing
    1.58
    respective
    1.51
     rispet
    1.48
     jeweils
    1.45
     respectivement
    1.44
    Activations Density 0.970%

    No Known Activations