© 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 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. 13079
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and commands in a code context

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

    Code related to parameters or controls

    np_acts-logits-general · gemini-2.0-flash

    code adding elements

    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
    transQ
    -0.66
    AndroidJUnit
    -0.63
    بوابة
    -0.62
    <eos>
    -0.60
     باشند
    -0.55
    ={`/
    -0.52
    toBe
    -0.51
    asto
    -0.49
    為
    -0.49
    ValueGenerated
    -0.49
    POSITIVE LOGITS
    Controls
    0.89
    ]")]
    0.79
    ReusableCell
    0.66
    seteq
    0.65
    nourriture
    0.65
    WebControls
    0.61
     Obrador
    0.60
    TacToe
    0.59
    الدراسه
    0.58
    seamnă
    0.58
    Activations Density 0.004%

    No Known Activations