© 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. 24-GEMMASCOPE-RES-16K
    11. 14740
    Prev
    Next
    INDEX
    Explanations

    links to external resources or websites

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

    preceding website or archive

    np_acts-logits-general · gemini-2.0-flash

    references and external links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </strong>
    -0.60
    ?
    -0.54
    ...>
    -0.53
    </em>
    -0.53
    ?)
    -0.51
    ：</
    -0.50
    ?}
    -0.49
    ?).
    -0.48
     =>
    -0.48
    Viited
    -0.48
    POSITIVE LOGITS
     Roskov
    0.75
    DockStyle
    0.71
    Datuak
    0.68
    دانشنامهٔ
    0.66
    PyExc
    0.66
     Normdatei
    0.63
    featureID
    0.62
    tagHelperRunner
    0.62
    存于互联网档案馆
    0.62
    脚注の使い方
    0.61
    Activations Density 0.120%

    No Known Activations