© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 1228
    Prev
    Next
    INDEX
    Explanations

    phrases related to online purchasing and assistance in acquiring products or services

    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
    RTEE
    -0.59
     AssemblyProduct
    -0.58
     gawas
    -0.55
    seamnă
    -0.52
    WriteBarrier
    -0.50
    Erstellt
    -0.50
    multirow
    -0.48
    ANZA
    -0.48
    naeus
    -0.47
    发表于
    -0.47
    POSITIVE LOGITS
    enumii
    0.56
     насељу
    0.56
    TextAppearance
    0.55
     թվական
    0.54
     SIMBAD
    0.53
     try
    0.51
     BitmapFactory
    0.49
    oux
    0.49
    +#+#
    0.48
    脚注の使い方
    0.48
    Activations Density 0.182%

    No Known Activations