© 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. 6959
    Prev
    Next
    INDEX
    Explanations

    mentions of specific geographical locations related to a particular event or entity

    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
    50
    +0.21
    1.4%
    1757
    +0.13
    0.8%
    32
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    645
    +0.21
    0.06
    1041
    +0.13
    0.05
    2004
    +0.12
    0.05
    Negative Logits
    <bos>
    -3.26
    /***
    -0.84
    ⓧ
    -0.74
    <?
    -0.73
    /**
    -0.69
    /*!
    -0.67
    HttpDelete
    -0.67
    /*
    -0.65
    
    -0.63
    lateinit
    -0.63
    POSITIVE LOGITS
     maroc
    1.53
     paradiso
    1.45
     maneu
    1.37
     bordeaux
    1.37
     Juf
    1.34
     milano
    1.34
     riva
    1.34
     lele
    1.34
     bandung
    1.34
     fta
    1.32
    Activations Density 0.137%

    No Known Activations