© 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. 25-GEMMASCOPE-RES-16K
    11. 8237
    Prev
    Next
    INDEX
    Explanations

    references to inmates' status and interactions within the prison system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    contentLoaded
    -0.68
    pannt
    -0.55
    tagHelperRunner
    -0.54
    ributions
    -0.53
     resourceCulture
    -0.52
    mybatisplus
    -0.51
    󠁢
    -0.50
    setScene
    -0.50
    AnchorTagHelper
    -0.49
     समीक्षक
    -0.49
    POSITIVE LOGITS
     prison
    1.79
     inmates
    1.78
     inmate
    1.74
     prisoners
    1.74
     Prison
    1.65
    Prison
    1.63
     prisoner
    1.62
    prison
    1.60
     prisons
    1.55
     PRISON
    1.49
    Activations Density 0.953%

    No Known Activations