© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14819
    Prev
    Next
    INDEX
    Explanations

    references to terms related to web cookies and privacy policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MemoryWarning
    -0.82
     resourceCulture
    -0.77
    الحياه
    -0.74
    featureID
    -0.71
    tvguidetime
    -0.70
    KommentareTeilen
    -0.67
    MockBean
    -0.67
    IndentedString
    -0.66
    MigrationBuilder
    -0.65
    
    -0.64
    POSITIVE LOGITS
     learn
    1.44
     Learn
    1.43
    Learn
    1.39
     Visit
    1.38
     read
    1.36
     visit
    1.35
    Visit
    1.29
    visit
    1.27
    learn
    1.25
     Click
    1.23
    Activations Density 0.162%

    No Known Activations