© 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. 2861
    Prev
    Next
    INDEX
    Explanations

    references to rooms or spaces in the context of renting or occupancy

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

    "room" or "rooms"

    np_acts-logits-general · gemini-2.0-flash

    room for, air, temperature

    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
    </tfoot>
    -0.66
    ]--;
    -0.61
    ]})
    -0.60
     Réponses
    -0.60
     ::=
    -0.59
    kozó
    -0.58
    ViewFeatures
    -0.56
     Ceinture
    -0.56
    !")
    -0.56
    揄
    -0.55
    POSITIVE LOGITS
     rooms
    1.09
     Room
    1.04
    rooms
    1.04
     Rooms
    1.02
     room
    0.97
     ROOM
    0.96
    Room
    0.93
    Rooms
    0.90
    room
    0.89
    ROOM
    0.88
    Activations Density 0.149%

    No Known Activations