© 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. 2-GEMMASCOPE-RES-16K
    11. 6892
    Prev
    Next
    INDEX
    Explanations

    connections related to "back up" actions or phrases indicating support and reinforcement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wiktionnaire
    -0.69
     Roskov
    -0.66
    OGND
    -0.66
     Signalez
    -0.66
     CreateTagHelper
    -0.62
    "}"
    -0.60
    ГЛА
    -0.60
    mongoose
    -0.59
    NgModule
    -0.59
    KURZBESCHREIBUNG
    -0.59
    POSITIVE LOGITS
     Backing
    0.66
     backing
    0.61
    naie
    0.56
    Backing
    0.54
     backup
    0.51
     backups
    0.51
     indietro
    0.50
     Backup
    0.49
     Bure
    0.48
    backup
    0.48
    Activations Density 0.116%

    No Known Activations