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. 10-GEMMASCOPE-RES-16K
    6. 4495
    Prev
    Next
    INDEX
    Explanations

    phrases related to returning or going back to a previous place or state

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/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.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pushFollow
    -0.76
     estimés
    -0.68
    awtextra
    -0.68
     متحده
    -0.62
     gyhoeddwyd
    -0.62
    kloped
    -0.62
    soort
    -0.60
    ahalli
    -0.59
     autorytatywna
    -0.58
    rxjs
    -0.58
    POSITIVE LOGITS
     retrace
    0.74
    back
    0.71
     tornare
    0.69
     Quid
    0.67
     indietro
    0.66
     back
    0.65
     homeward
    0.65
     Chama
    0.65
     Reif
    0.64
    Back
    0.64
    Activations Density 0.106%

    No Known Activations