© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 5306
    Prev
    Next
    INDEX
    Explanations

    discussions related to statistical methods and estimators, particularly in the context of research methodologies

    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
     synced
    -0.58
     suéter
    -0.57
    crypted
    -0.53
    fractal
    -0.53
    IUrlHelper
    -0.52
    SafeAreaView
    -0.52
     hanger
    -0.52
    Personensuche
    -0.52
    findpost
    -0.51
    MIDDLEWARE
    -0.51
    POSITIVE LOGITS
     Walkover
    0.66
     problèmes
    0.62
     problema
    0.58
    enfants
    0.58
     generality
    0.57
     generali
    0.57
    ENSIONS
    0.57
     problème
    0.56
     problem
    0.56
     vectoriales
    0.56
    Activations Density 3.248%

    No Known Activations