© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 16255
    Prev
    Next
    INDEX
    Explanations

    symbols and notation used in scientific citations or references

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

    References/citations (e.g., [@CR10])

    np_acts-logits-general · gemini-2.0-flash

    > ORM

    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
    yntaxException
    -1.00
     ComVisible
    -0.95
    </caption>
    -0.89
     سكانية
    -0.86
    出版年
    -0.85
    djangoproject
    -0.81
    קישורים
    -0.81
    NUMX
    -0.81
     initComponents
    -0.80
    noinspection
    -0.79
    POSITIVE LOGITS
    <eos>
    0.67
    :-
    0.58
    ↵↵
    0.57
     :
    0.56
    .”
    0.55
    _
    0.55
    ”
    0.53
    !.
    0.51
    :.
    0.51
    ↵↵↵↵
    0.50
    Activations Density 1.965%

    No Known Activations