© 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. 5698
    Prev
    Next
    INDEX
    Explanations

    terms related to legal proceedings and charges

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

    legal prosecution

    np_acts-logits-general · gemini-2.0-flash

    prosecutor and prosecution

    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
    rrggbb
    -0.62
    SOUNDBITE
    -0.56
     CreateTagHelper
    -0.52
    WriteTagHelper
    -0.51
    FunctionFlags
    -0.50
     يتيمه
    -0.49
     ríos
    -0.48
    obium
    -0.48
    GIVEREF
    -0.47
    Geplaatst
    -0.47
    POSITIVE LOGITS
     prosecutors
    1.36
     prosecutor
    1.32
     prosecution
    1.29
     prosecuting
    1.25
    Prosec
    1.21
     prosec
    1.20
     Prosec
    1.19
     prosecute
    1.13
     Prosecutor
    1.13
    Prosecutors
    1.11
    Activations Density 0.762%

    No Known Activations