© 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. 1929
    Prev
    Next
    INDEX
    Explanations

    verbs related to the initiation of actions or processes

    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
    titura
    -0.64
    gypti
    -0.63
    readyState
    -0.63
    enumi
    -0.63
    তথ্যসূত্র
    -0.60
    Ảnh
    -0.59
     Sleep
    -0.59
    vedev
    -0.59
    ocarp
    -0.58
     Coss
    -0.58
    POSITIVE LOGITS
     started
    1.98
     Started
    1.83
    started
    1.73
     STARTED
    1.64
    Started
    1.62
    STARTED
    1.33
     begun
    1.31
     commenced
    1.15
     began
    1.04
     initiated
    0.97
    Activations Density 0.123%

    No Known Activations