© 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. 8-GEMMASCOPE-RES-16K
    6. 3566
    Prev
    Next
    INDEX
    Explanations

    references to programming or library imports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -1.55
    AsUp
    -1.12
    Vidite
    -1.10
    EDEFAULT
    -1.10
    PreferredItem
    -1.06
    GEBURTSDATUM
    -1.05
    windowFixed
    -1.02
    featureID
    -1.00
    LookAnd
    -0.99
    oredCriteria
    -0.98
    POSITIVE LOGITS
     
    0.59
    .
    0.55
     A
    0.55
    <tr>
    0.54
     It
    0.54
    0.52
    <unused63>
    0.50
     D
    0.49
     The
    0.49
    ↵↵
    0.49
    Activations Density 0.017%

    No Known Activations