© 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. 14938
    Prev
    Next
    INDEX
    Explanations

    specific programming and code-related terms

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

    Code snippets or program installation instructions

    np_acts-logits-general · gemini-2.0-flash

    installation notes

    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
     Paglinawan
    -0.87
    Personendaten
    -0.85
    ')")
    -0.81
    ).\\
    -0.81
    VersionUID
    -0.79
    ,:);
    -0.79
    .")]
    -0.78
    endphp
    -0.78
     ExecuteAsync
    -0.77
    ngdoc
    -0.77
    POSITIVE LOGITS
     Note
    1.26
     NOTE
    1.25
     (
    1.25
    Note
    1.24
     note
    1.22
    NOTE
    1.17
    note
    1.13
    ※
    0.98
     *
    0.95
     (*
    0.94
    Activations Density 0.278%

    No Known Activations