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. 15-GEMMASCOPE-RES-16K
    6. 5188
    Prev
    Next
    INDEX
    Explanations

    Java class structure elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    发表于
    -0.76
     ['./
    -0.74
    httphttps
    -0.73
    PerformLayout
    -0.73
    μφωνα
    -0.71
    onViewCreated
    -0.69
     للمعارف
    -0.66
    ^(@)
    -0.65
    Література
    -0.65
    yntaxException
    -0.63
    POSITIVE LOGITS
     getter
    0.58
    OGND
    0.57
    bed
    0.50
     bed
    0.50
    ForTesting
    0.49
     VIAF
    0.48
    曝
    0.47
    desta
    0.45
     getters
    0.44
    iettivo
    0.44
    Activations Density 0.161%

    No Known Activations