© 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. 10359
    Prev
    Next
    INDEX
    Explanations

    programming terms and structures related to data or message handling

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

    Followed by curly brackets containing get/set

    np_acts-logits-general · gemini-2.0-flash

    message, response, request, flight, val

    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
    +#+#
    -0.62
    "]);
    -0.59
    ]));
    -0.58
    "])
    -0.55
     nahilalakip
    -0.54
    "));
    -0.54
    ]);
    -0.54
    rubin
    -0.53
    AddRange
    -0.53
    __(/*!
    -0.53
    POSITIVE LOGITS
     itſelf
    0.69
     InputDecoration
    0.68
     theſe
    0.66
     myſelf
    0.65
     himſelf
    0.64
     cauſe
    0.63
     preſent
    0.61
     ſhe
    0.61
     poffible
    0.60
     EventArgs
    0.60
    Activations Density 0.140%

    No Known Activations