© 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. 4-GEMMASCOPE-RES-16K
    11. 12986
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate varying degrees of intensity or magnitude, often related to descriptions or comparisons

    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
     termica
    -0.68
    setof
    -0.58
    lainen
    -0.57
     Zuw
    -0.56
     arries
    -0.56
     Stabilization
    -0.56
     deber
    -0.56
     straighten
    -0.56
     vettor
    -0.55
     rosse
    -0.55
    POSITIVE LOGITS
    AddTagHelper
    0.91
    PreferredItem
    0.89
    AnchorStyles
    0.82
    InjectAttribute
    0.79
    CppMethod
    0.76
    يميديا
    0.73
    ActionCreators
    0.72
    UIControlState
    0.71
    Abitanti
    0.70
    expandindo
    0.70
    Activations Density 0.774%

    No Known Activations