Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 8784
    Prev
    Next
    INDEX
    Explanations

    the presence of various structural elements in texts, such as curly braces and other syntax characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ThroughAttribute
    -1.07
    TintMode
    -0.94
     تضيفلها
    -0.88
    nodoc
    -0.87
    GIVEREF
    -0.85
     SwitchCompat
    -0.84
     typelib
    -0.82
    SharedCtor
    -0.82
    webElement
    -0.81
    exitRule
    -0.81
    POSITIVE LOGITS
    nsf
    0.49
    “
    0.47
    】
    0.46
    
    0.45
    </u>
    0.45
     setTimeout
    0.43
    ★
    0.43
    )
    0.43
    sel
    0.42
    alt
    0.42
    Activations Density 0.498%

    No Known Activations