© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 27918
    Prev
    Next
    INDEX
    Explanations

    indicators of legal proceedings or formal documentation

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

    defendant or quoted text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteTagHelper
    -1.19
    "},
    -1.16
     EconPapers
    -1.15
    '},
    -1.15
    =$?
    -1.12
    __':
    -1.09
     CreateTagHelper
    -1.08
    ]))
    -1.08
    __':
    -1.07
    ")));
    -1.06
    POSITIVE LOGITS
     The
    0.68
    The
    0.65
     were
    0.59
    http
    0.57
     is
    0.57
     was
    0.57
                
    0.54
    格
    0.54
      
    0.54
     are
    0.54
    Activations Density 0.016%

    No Known Activations