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. 17-GEMMASCOPE-RES-16K
    6. 11170
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to software and network functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estimés
    -0.58
    -
    -0.55
     
    -0.55
    edu
    -0.51
    con
    -0.51
     (
    -0.51
     [
    -0.50
    p
    -0.49
    '],$
    -0.48
     “
    -0.48
    POSITIVE LOGITS
    存于互联网档案馆
    0.87
    glGen
    0.81
     fallu
    0.71
    addContainerGap
    0.70
    Portale
    0.68
     tartalomajánló
    0.67
    ContentAsync
    0.66
     MonoBehaviour
    0.65
    Gemeinsame
    0.65
    Obrázky
    0.64
    Activations Density 0.082%

    No Known Activations