© 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. 12-GEMMASCOPE-RES-16K
    6. 10742
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions related to functions and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     then
    -0.55
     the
    -0.53
    .
    -0.51
    ↵↵
    -0.47
     an
    -0.47
     in
    -0.46
    ated
    -0.43
    う
    -0.42
    <eos>
    -0.42
    ).
    -0.41
    POSITIVE LOGITS
     Мексичка
    1.15
    InjectAttribute
    1.11
     '{@
    1.08
     '\\;'
    1.06
    تقاوى
    1.02
    Datuak
    1.02
    SourceChecksum
    1.01
    EDEFAULT
    0.94
    ChildScrollView
    0.94
     wikipagina
    0.94
    Activations Density 0.490%

    No Known Activations