© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 5983
    Prev
    Next
    INDEX
    Explanations

    descriptions related to spatial orientation within a location

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    897
    +0.17
    0.8%
    732
    +0.14
    0.7%
    30
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    897
    +0.17
    0.03
    30
    +0.14
    0.02
    1385
    +0.13
    0.03
    Negative Logits
    <bos>
    -1.38
    ///**
    -0.68
    ////////////
    -0.67
    Portály
    -0.65
    lateinit
    -0.61
    ///////////////
    -0.59
    GenerationType
    -0.58
    -0.57
    SaveChangesAsync
    -0.57
    djangoproject
    -0.56
    POSITIVE LOGITS
     Inner
    1.27
     inner
    1.13
     eiffel
    1.11
    Inner
    1.08
     véhic
    1.07
     INNER
    1.07
     Outer
    1.07
     swarovski
    1.06
    capulco
    1.01
     napoli
    0.99
    Activations Density 0.173%

    No Known Activations