© 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. 22-GEMMASCOPE-RES-16K
    11. 8128
    Prev
    Next
    INDEX
    Explanations

    words related to legal terminology and concepts of conviction or acquittal

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

    starting with "con" or "uncon"

    np_acts-logits-general · gemini-2.0-flash

    con/uncon words

    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
    bootstrapcdn
    -0.78
    pography
    -0.65
     finito
    -0.64
     يتيمه
    -0.61
    ANTO
    -0.59
    ZING
    -0.59
     stolen
    -0.58
     rasa
    -0.57
    ineno
    -0.57
     stole
    -0.57
    POSITIVE LOGITS
     inoxidable
    0.47
     XCTest
    0.46
    UnusedPrivate
    0.46
     ilma
    0.46
    ingeki
    0.42
     vocación
    0.42
    rog
    0.42
     aplican
    0.42
    AutoScaleMode
    0.41
    ardı
    0.40
    Activations Density 0.407%

    No Known Activations