© 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. 4-GEMMASCOPE-RES-16K
    6. 9496
    Prev
    Next
    INDEX
    Explanations

    phrases indicating existence or necessity, such as "to be" constructions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <?
    -0.86
    +#+#
    -0.83
    DebuggerNonUser
    -0.82
    stdc
    -0.82
     Roskov
    -0.81
    dited
    -0.76
    WebVitals
    -0.75
    aarrggbb
    -0.74
     Wikimédia
    -0.73
     AttributeSet
    -0.72
    POSITIVE LOGITS
     there
    1.03
     no
    0.89
    there
    0.84
     There
    0.82
    There
    0.80
    Есть
    0.79
     есть
    0.77
     plenty
    0.77
     existe
    0.75
    還有
    0.74
    Activations Density 0.201%

    No Known Activations