© 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. 4063
    Prev
    Next
    INDEX
    Explanations

    terms related to upgrades and improvements in facilities or infrastructure

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

    Locations within buildings

    np_acts-logits-general · gemini-2.0-flash

    building locations and units

    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
     CITIES
    -0.67
    tvguidetime
    -0.64
    JNIEnv
    -0.62
    cities
    -0.62
     domicilio
    -0.62
     Италијани
    -0.60
     villes
    -0.60
    Datuak
    -0.59
     agricoles
    -0.58
    DeleteCommand
    -0.58
    POSITIVE LOGITS
     downstairs
    1.15
     rooms
    1.15
     upstairs
    1.14
     hallways
    1.14
     hallway
    1.09
     room
    1.05
     floor
    1.03
     lounge
    1.00
     corridors
    0.99
     staff
    0.99
    Activations Density 0.559%

    No Known Activations