© 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. 2-GEMMASCOPE-RES-16K
    11. 7054
    Prev
    Next
    INDEX
    Explanations

    sentences discussing policy decisions or legal proceedings related to individual rights and government actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     duele
    -0.70
    Personendaten
    -0.70
     fermés
    -0.70
    MessageTagHelper
    -0.69
     Мексичка
    -0.68
    ISupport
    -0.67
    Бахар
    -0.66
     <>",
    -0.65
     AssemblyCulture
    -0.64
    principalColumn
    -0.63
    POSITIVE LOGITS
    ParallelGroup
    0.47
     cr
    0.46
    ด
    0.44
     stol
    0.43
     Bond
    0.42
    i
    0.42
    zen
    0.41
    lfs
    0.41
     protoimpl
    0.41
     uts
    0.40
    Activations Density 0.156%

    No Known Activations