© 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. 24-GEMMASCOPE-RES-16K
    11. 2437
    Prev
    Next
    INDEX
    Explanations

    terms related to prison and inmate experiences

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

    prisons and inmates

    np_acts-logits-general · gemini-2.0-flash

    prison dormitories and inmates

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    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
    -0.72
    SourceChecksum
    -0.64
    󠁢
    -0.64
    QMetaType
    -0.62
    findpost
    -0.60
    mybatisplus
    -0.60
    AnchorTagHelper
    -0.60
    ributions
    -0.59
     resourceCulture
    -0.57
     estekak
    -0.57
    POSITIVE LOGITS
     inmates
    1.48
     inmate
    1.41
     prisoners
    1.39
     prison
    1.35
     prisoner
    1.28
    prison
    1.21
    Prison
    1.21
     incarcerated
    1.20
     Prison
    1.19
     prisons
    1.13
    Activations Density 0.711%

    No Known Activations