© 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. 16194
    Prev
    Next
    INDEX
    Explanations

    phrases that highlight specific factors, particularly emphasizing distinctions and cases related to populations or conditions

    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
     continúas
    -0.52
    euse
    -0.49
    ceans
    -0.49
    oczes
    -0.49
    <caption>
    -0.48
    arga
    -0.48
     puol
    -0.47
     slew
    -0.46
     promp
    -0.46
    ...
    -0.45
    POSITIVE LOGITS
     Particularly
    1.08
     Especially
    1.01
    Especially
    0.99
     especially
    0.98
     particularly
    0.97
    particularly
    0.94
    especially
    0.92
     PARTICULAR
    0.91
     specialmente
    0.89
     especialmente
    0.88
    Activations Density 0.488%

    No Known Activations