© 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. 0-RES-JB
    11. 108
    Prev
    Next
    INDEX
    Explanations

    locations and event information stated in a specific format

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.14
    0.7%
    1978
    +0.05
    0.3%
    1343
    +0.04
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1859
    +0.14
    0.06
    1326
    +0.05
    0.06
    832
    +0.04
    0.05
    Negative Logits
    <bos>
    -1.75
    <?
    -1.04
    /**
    -0.93
    
    -0.92
    ⓧ
    -0.90
     springfox
    -0.81
    /*
    -0.76
    <tfoot>
    -0.68
    <?
    -0.66
    #
    -0.65
    POSITIVE LOGITS
     catég
    1.43
     délib
    1.43
     maneu
    1.41
     véhic
    1.39
     affor
    1.39
     habile
    1.37
     accla
    1.35
     stockholm
    1.33
     strick
    1.29
     impra
    1.27
    Activations Density 0.069%

    No Known Activations