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. 7-GEMMASCOPE-RES-16K
    6. 14639
    Prev
    Next
    INDEX
    Explanations

    references to the direction or region related to "East"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageTagHelper
    -1.23
    #+#
    -1.00
    profen
    -0.99
     propOrder
    -0.96
    HideInInspector
    -0.94
    bufio
    -0.93
     Solskjaer
    -0.93
     Gurgaon
    -0.89
    DebuggerNonUser
    -0.89
    __;
    -0.88
    POSITIVE LOGITS
     East
    1.74
    East
    1.71
     EAST
    1.55
     east
    1.40
    EAST
    1.31
    east
    1.29
     Eastern
    1.15
     eastern
    1.03
     Øst
    1.02
     Eastman
    1.02
    Activations Density 0.039%

    No Known Activations