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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8821
    Prev
    Next
    INDEX
    Explanations

    words related to simplicity and straightforwardness

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

    "simple"

    np_acts-logits-general · gemini-2.0-flash

    simple specific nouns

    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
     للمعارف
    -0.85
    OrBuilder
    -0.70
     AssemblyTitle
    -0.70
     passim
    -0.70
    HideFlags
    -0.69
    })*/
    -0.69
     تانيه
    -0.68
    verifyException
    -0.68
    PyErr
    -0.68
    endregion
    -0.65
    POSITIVE LOGITS
     Simple
    1.17
    Simple
    1.09
     simple
    1.09
     SIMPLE
    1.07
    SIMPLE
    1.01
    simple
    0.99
     simpel
    0.89
     Plain
    0.86
     简单
    0.84
    简单的
    0.82
    Activations Density 0.113%

    No Known Activations