© 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. 18-GEMMASCOPE-RES-16K
    11. 48
    Prev
    Next
    INDEX
    Explanations

    concepts related to legal proceedings and their principles

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

    Followed by "of"

    np_acts-logits-general · gemini-2.0-flash

    concept of

    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
     صوتيه
    -0.57
    twimg
    -0.52
     noqa
    -0.50
    ering
    -0.49
     مرئيه
    -0.48
    évaluateur
    -0.47
    zzleHttp
    -0.47
     дописавши
    -0.46
    arResult
    -0.45
    SCRIBE
    -0.44
    POSITIVE LOGITS
     of
    0.80
    AndroidJUnit
    0.66
    __*/
    0.65
     notion
    0.64
     concept
    0.59
     called
    0.56
    akyti
    0.56
    <caption>
    0.56
    ########.
    0.55
     TextInputType
    0.55
    Activations Density 0.370%

    No Known Activations