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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1665
    Prev
    Next
    INDEX
    Explanations

    names of geographical locations, particularly cities and religious figures

    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
    1703
    +0.09
    0.3%
    1343
    +0.08
    0.3%
    50
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.09
    0.15
    283
    +0.08
    0.04
    724
    +0.08
    0.07
    Negative Logits
    <bos>
    -1.27
    
    -0.93
    ⓧ
    -0.92
    /**
    -0.84
    <?
    -0.83
    habited
    -0.67
    /*
    -0.65
     springfox
    -0.64
     reinstate
    -0.64
    <?
    -0.64
    POSITIVE LOGITS
     meis
    1.14
     Bibl
    1.07
     maniere
    1.00
     poliuret
    0.99
     tille
    0.99
     Décembre
    0.98
     Traité
    0.97
     ideen
    0.96
     Strukt
    0.96
     Kategor
    0.96
    Activations Density 1.001%

    No Known Activations