© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 1862
    Prev
    Next
    INDEX
    Explanations

    numerical patterns or sequences

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

    Time codes in ".srt" subtitle files

    np_acts-logits-general · gemini-2.0-flash

    timestamps or time codes

    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
    ])));
    -0.76
    ']))
    
    -0.74
     CreateTagHelper
    -0.73
    }))
    
    -0.69
    UrlResolution
    -0.68
    ########.
    -0.68
    )}}{
    -0.67
    #+#
    -0.65
    (")");
    -0.64
    )]);
    -0.63
    POSITIVE LOGITS
    日閲覧
    0.65
     vestiti
    0.57
     uſed
    0.53
    ſelf
    0.51
     clf
    0.51
    ніципа
    0.50
     houſe
    0.50
     Hinduism
    0.49
     caufe
    0.49
     Turquie
    0.48
    Activations Density 0.125%

    No Known Activations