© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 2035
    Prev
    Next
    INDEX
    Explanations

    key terms related to legal and regulatory contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    diagrams, families, or structures

    np_acts-logits-general · gemini-2.0-flash

    diverse topics and contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.78
    ]));
    -0.73
    +#+#
    -0.70
    ]))
    -0.67
    uxxxx
    -0.67
     fevere
    -0.67
     متعلقه
    -0.66
     AssemblyProduct
    -0.66
    󠁢
    -0.65
    ]_{\
    -0.64
    POSITIVE LOGITS
     structure
    0.61
    path
    0.59
    -
    0.56
     profile
    0.54
     parameters
    0.54
     path
    0.53
    group
    0.51
     types
    0.51
     development
    0.49
    types
    0.49
    Activations Density 1.589%

    No Known Activations