© 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. 1950
    Prev
    Next
    INDEX
    Explanations

    projects and programs related to funding and initiatives across various sectors

    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
    +0.10
    0.5%
    1870
    +0.10
    0.5%
    2036
    +0.04
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.10
    0.03
    1385
    +0.10
    0.08
    1499
    +0.04
    0.08
    Negative Logits
    <bos>
    -1.92
    ⓧ
    -1.14
    
    -1.03
    <?
    -0.99
    /**
    -0.99
    <?
    -0.90
    /***
    -0.85
     négociations
    -0.83
     prochaines
    -0.79
     pouvoirs
    -0.78
    POSITIVE LOGITS
     maroc
    1.39
     lele
    1.34
     bandung
    1.33
     thuy
    1.31
     jaya
    1.28
     riva
    1.24
     ananas
    1.24
     meis
    1.22
     roul
    1.20
     cannes
    1.18
    Activations Density 0.446%

    No Known Activations