© 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. 1472
    Prev
    Next
    INDEX
    Explanations

    mention of restrictions, limitations, and consequences

    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
    +0.08
    0.3%
    757
    +0.07
    0.3%
    1265
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    757
    +0.08
    0.04
    188
    +0.07
    0.04
    411
    +0.07
    0.03
    Negative Logits
    <bos>
    -1.36
    ⓧ
    -1.10
    
    -1.01
    /**
    -0.97
    <?
    -0.96
    /***
    -0.92
    /*!
    -0.83
     procédures
    -0.78
     déclarations
    -0.77
    <?
    -0.76
    POSITIVE LOGITS
     shortcomings
    1.54
     weaknesses
    1.48
     drawbacks
    1.45
     limitations
    1.44
     flaws
    1.42
     jaya
    1.31
     bandung
    1.28
     imperfections
    1.28
     haup
    1.27
     sentra
    1.26
    Activations Density 0.228%

    No Known Activations