© 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. 8-GEMMASCOPE-RES-16K
    6. 3632
    Prev
    Next
    INDEX
    Explanations

    lines indicating user confirmation or action prompts in an interactive interface

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ритори
    -0.63
    ]();
    -0.59
    XmlAccessorType
    -0.57
    новништво
    -0.56
     насељу
    -0.54
     चाहिए
    -0.49
    IBO
    -0.45
    ్రామ
    -0.44
    وفاته
    -0.44
    protoc
    -0.44
    POSITIVE LOGITS
     AttributeSet
    0.66
    NegativeButton
    0.61
    tionnaire
    0.59
     AssemblyCulture
    0.59
     onBackPressed
    0.57
    SpringBootTest
    0.57
     Option
    0.56
    databinding
    0.56
     MainAxisSize
    0.55
    OPTION
    0.55
    Activations Density 0.320%

    No Known Activations