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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 2252
    Prev
    Next
    INDEX
    Explanations

    conditions or scenarios related to legal proceedings or judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IUrlHelper
    -0.74
    олові
    -0.74
    gorithm
    -0.71
    etheless
    -0.65
    itename
    -0.65
    phazard
    -0.63
    tableFuture
    -0.62
     defStyleAttr
    -0.62
    ratulations
    -0.62
    iffance
    -0.61
    POSITIVE LOGITS
    Viitteet
    0.61
    のではなく
    0.51
    Di
    0.50
    Kapp
    0.48
    All
    0.47
    zk
    0.47
     TestBed
    0.47
    ште
    0.46
    кк
    0.46
     Ahead
    0.46
    Activations Density 0.486%

    No Known Activations