© 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. 2-GEMMASCOPE-RES-16K
    6. 1952
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and structures, particularly in code syntax

    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
    rungsseite
    -1.10
    parsedMessage
    -1.01
     vPvB
    -1.00
    CppMethod
    -0.93
     Jefus
    -0.92
     SwitchCompat
    -0.91
     itſelf
    -0.90
    ^(@)
    -0.85
     whoſe
    -0.85
     newOwner
    -0.84
    POSITIVE LOGITS
     (
    0.41
     en
    0.38
     
    0.38
    <h1>
    0.37
    ↵
    0.37
     -
    0.36
    .
    0.35
    <h2>
    0.35
     in
    0.35
    一
    0.34
    Activations Density 0.241%

    No Known Activations