© 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. 40
    Prev
    Next
    INDEX
    Explanations

    relationships between concepts or variables in analytical contexts

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

    Preceding words of common words

    np_acts-logits-general · gemini-2.0-flash

    mathematical operation packet

    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
    .
    -1.69
    。
    -1.10
    ).
    -1.02
    ;
    -0.99
    $.
    -0.99
    }$.
    -0.92
    ।
    -0.91
    !
    -0.91
    %.
    -0.85
    .\\
    -0.85
    POSITIVE LOGITS
    NameInMap
    1.10
    )";
    1.06
    webElementXpaths
    1.05
     CreateTagHelper
    1.05
    AxisAlignment
    0.99
    клопе
    0.97
     GenerationType
    0.95
    <bos>
    0.93
    دانشنامهٔ
    0.93
    ⓧ
    0.91
    Activations Density 1.733%

    No Known Activations