Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 613
    Prev
    Next
    INDEX
    Explanations

    phrases related to record deals and musical contracts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AllowUser
    -0.60
     surla
    -0.55
    XmlAccessorType
    -0.54
    angliski
    -0.53
    }-${
    -0.51
    RTEX
    -0.50
    曖昧さ回避
    -0.50
     للاسماء
    -0.50
     Olympedia
    -0.50
     AssemblyCulture
    -0.49
    POSITIVE LOGITS
     labels
    1.14
     label
    1.06
     Labels
    0.90
    label
    0.87
    labels
    0.84
     Label
    0.84
    Labels
    0.80
    Label
    0.75
     record
    0.75
     indépendant
    0.75
    Activations Density 0.184%

    No Known Activations