© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 12140
    Prev
    Next
    INDEX
    Explanations

    terms related to legal and procedural contexts

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

    ending in "ed" or "ted"

    np_acts-logits-general · gemini-2.0-flash

    past tense verbs

    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
    pulumi
    -0.76
    mybatisplus
    -0.63
    IDATE
    -0.61
    entukan
    -0.61
    WriteBarrier
    -0.58
    GARET
    -0.58
    хьтан
    -0.57
    initializeApp
    -0.57
    PendingIntent
    -0.56
    Filmografie
    -0.54
    POSITIVE LOGITS
    ed
    3.23
    ED
    1.82
    ized
    1.55
    ated
    1.39
    ted
    1.31
    edly
    1.17
    ened
    1.17
    ned
    1.07
    edf
    1.05
    ued
    1.01
    Activations Density 0.375%

    No Known Activations