© 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-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 11696
    Prev
    Next
    INDEX
    Explanations

    references to locations, particularly apartments and stairs, within a narrative context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.53
     PopupWindow
    -0.51
    msgTypes
    -0.50
    GEBURTS
    -0.50
    Personendaten
    -0.49
     DialogInterface
    -0.46
     createSlice
    -0.46
    awtextra
    -0.46
     kasarigan
    -0.46
    batore
    -0.45
    POSITIVE LOGITS
     hallway
    1.48
     corridor
    1.38
     hallways
    1.34
     corridors
    1.25
     pasillo
    1.24
     foyer
    1.16
     lobby
    1.15
     lobbies
    1.07
     hall
    1.05
     Corridor
    1.04
    Activations Density 0.187%

    No Known Activations