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

    Neuronpedia

    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. 22-GEMMASCOPE-RES-16K
    11. 8427
    Prev
    Next
    INDEX
    Explanations

    structured data related to software or device specifications

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

    software or hardware version numbers

    np_acts-logits-general · gemini-2.0-flash

    version information

    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
    nemone
    -0.42
    istorante
    -0.38
    umbag
    -0.38
    velopes
    -0.37
    otheses
    -0.37
    Lamb
    -0.36
    yns
    -0.36
    meable
    -0.35
    lgica
    -0.35
     palpit
    -0.35
    POSITIVE LOGITS
    version
    1.09
     version
    1.08
    Version
    1.05
     Version
    1.02
     platform
    0.98
     VERSION
    0.97
     Platform
    0.97
     Versions
    0.94
     versions
    0.94
    版本
    0.94
    Activations Density 0.590%

    No Known Activations