© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 12803
    Prev
    Next
    INDEX
    Explanations

    information related to geographical locations, specifically mountains and their characteristics

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    906
    +0.16
    0.5%
    872
    +0.15
    0.5%
    1120
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.16
    0.09
    766
    +0.15
    0.05
    51
    +0.14
    0.03
    Negative Logits
     geforce
    -0.79
     logitech
    -0.73
     gopro
    -0.70
     kram
    -0.69
     ryzen
    -0.68
     stoff
    -0.68
     airpods
    -0.68
     motorola
    -0.67
     scaff
    -0.65
     kog
    -0.65
    POSITIVE LOGITS
     region
    0.59
     geographical
    0.58
     geographically
    0.57
     geographic
    0.56
     regions
    0.54
     inhabited
    0.52
    inhabited
    0.52
     anhyd
    0.51
     borders
    0.51
     topography
    0.51
    Activations Density 0.873%

    No Known Activations