© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 5744
    Prev
    Next
    INDEX
    Explanations

    terms related to geographical locations and spatial references

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

    location and spatial information

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     porta
    -0.31
    3
    -0.30
    Dest
    -0.30
    就
    -0.30
     Vers
    -0.29
     carry
    -0.29
    "
    -0.29
    <eos>
    -0.29
     carries
    -0.28
     tỏ
    -0.28
    POSITIVE LOGITS
    LLocation
    1.09
     Location
    1.05
     location
    0.99
    Location
    0.98
     getLocation
    0.91
     LOCATION
    0.90
    location
    0.85
    SharedCtor
    0.85
    LOCATION
    0.85
    LocationManager
    0.84
    Activations Density 0.001%

    No Known Activations