Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11624
    Prev
    Next
    INDEX
    Explanations

    phrases related to returning or going back to a location, particularly at the end of an activity or journey.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @myinzi123

    phrases related to returning or going back to a previous location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ujednoznacz
    -0.50
     SwitchCompat
    -0.49
    makeConstraints
    -0.48
     beginnetje
    -0.47
    ゴリー
    -0.46
    icrous
    -0.46
    LocationManager
    -0.45
    GEBURTSDATUM
    -0.45
    Географи
    -0.44
    LookAnd
    -0.44
    POSITIVE LOGITS
     returning
    0.58
     wró
    0.57
     pulang
    0.57
     home
    0.54
     thuis
    0.52
     indietro
    0.50
     terug
    0.50
     zurück
    0.50
     kembali
    0.49
     returned
    0.48
    Activations Density 0.239%

    No Known Activations