© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13844
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and terms

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

    Code, math, or definitions

    np_acts-logits-general · gemini-2.0-flash

    biological and code terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.48
    Fär
    -0.42
     ChromeDriver
    -0.42
    optarg
    -0.39
     strtok
    -0.39
    ंदीखरीदारी
    -0.39
     Volkes
    -0.37
     getopt
    -0.37
    AnchorTagHelper
    -0.37
    Tikang
    -0.37
    POSITIVE LOGITS
     transférez
    0.59
    MigrationBuilder
    0.51
     transfieras
    0.49
    SaveChangesAsync
    0.48
     otomatig
    0.46
     Infórmanos
    0.44
    ExecuteReader
    0.44
    цездатний
    0.42
     Roskov
    0.41
     correctes
    0.40
    Activations Density 23.460%

    No Known Activations