© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 11081
    Prev
    Next
    INDEX
    Explanations

    terms related to the structure and behavior of cells and their environments

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

    ending in "-ly" or relating to cells

    np_acts-logits-general · gemini-2.0-flash

    adverbs of location and manner

    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
     ​​
    -1.10
    %)$
    -0.90
     CreateTagHelper
    -0.89
    rungsseite
    -0.88
     SwiftUI
    -0.86
    +#+#
    -0.84
    !*\
    -0.83
     Alcott
    -0.81
     Bioaccumulative
    -0.79
     nakalista
    -0.78
    POSITIVE LOGITS
    ly
    3.20
    LY
    1.95
    ally
    1.46
    mente
    1.40
    fully
    1.36
    theless
    1.27
    tably
    1.13
    ably
    1.07
    了
    1.06
    nya
    1.05
    Activations Density 0.997%

    No Known Activations