© 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. 24-GEMMASCOPE-RES-16K
    11. 7583
    Prev
    Next
    INDEX
    Explanations

    terms related to suspects and their legal implications

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

    Follows "su" (often capitalized)

    np_acts-logits-general · gemini-2.0-flash

    sus/su followed by specific endings

    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
    SharedCtor
    -0.71
    IntoConstraints
    -0.68
    InjectMocks
    -0.63
    SharedDtor
    -0.56
     &___
    -0.54
    Unmarshal
    -0.53
    DotNetBar
    -0.52
    EndInit
    -0.51
    Superficie
    -0.50
     Audiodateien
    -0.49
    POSITIVE LOGITS
     виправивши
    0.67
     hiér
    0.61
    nah
    0.59
    Rhestr
    0.53
     scro
    0.53
     tudom
    0.53
    aarrggbb
    0.52
     scolaire
    0.51
    féle
    0.51
     Igual
    0.50
    Activations Density 0.263%

    No Known Activations