© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2037
    Prev
    Next
    INDEX
    Explanations

    references to mercy and its role in the context of criminal sentencing

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

    legal and judicial terminology related to sentencing and criminal justice.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eseorang
    -0.53
    期刊论文
    -0.51
     szóci
    -0.47
     propOrder
    -0.47
    Glej
    -0.45
     murni
    -0.45
    jenigen
    -0.43
    jenige
    -0.43
    ynı
    -0.43
     dichas
    -0.43
    POSITIVE LOGITS
    Portail
    0.52
    ⤹
    0.51
    TextHelper
    0.49
     betweenstory
    0.49
     Kass
    0.45
     deceleration
    0.45
     calendriers
    0.45
     Kas
    0.43
     MainAxisSize
    0.42
    🧰
    0.41
    Activations Density 0.160%

    No Known Activations