© 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. 18-GEMMASCOPE-RES-16K
    11. 11274
    Prev
    Next
    INDEX
    Explanations

    activities related to movement and exploration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Movement or activity in different locations

    np_acts-logits-general · gemini-2.0-flash

    wandering about

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mostaza
    -0.44
    Rising
    -0.42
     pře
    -0.40
    trzyma
    -0.40
    Atoi
    -0.40
     getLogin
    -0.40
     direct
    -0.40
     moment
    -0.40
    עו
    -0.39
    Direct
    -0.39
    POSITIVE LOGITS
     aisles
    0.87
     around
    0.85
     streets
    0.82
    Personensuche
    0.81
     alleys
    0.79
    NegativeButton
    0.79
    IUrlHelper
    0.78
     corridors
    0.77
    tagHelperRunner
    0.77
    queryInterface
    0.76
    Activations Density 0.271%

    No Known Activations