© 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. 1437
    Prev
    Next
    INDEX
    Explanations

    text related to online forum posts and technical discussions

    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
    1419
    +0.13
    0.4%
    1804
    +0.12
    0.4%
    536
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    536
    +0.13
    0.08
    1607
    +0.12
    0.07
    1120
    +0.09
    0.08
    Negative Logits
    <?
    -1.47
    /**
    -1.42
    <?
    -1.35
    /*
    -1.31
    
    -1.24
    ⓧ
    -1.11
    Lmfao
    -1.09
    URBANA
    -1.02
    Ikr
    -0.98
    Hahahahaha
    -0.94
    POSITIVE LOGITS
    <bos>
    1.69
     مشين
    1.56
     CreateTagHelper
    1.39
     autorytatywna
    1.32
     resourceCulture
    1.23
     كومونز
    1.19
    IndentedString
    1.14
    GraphicsUnit
    1.12
    例文帳に追加
    1.09
    SharedDtor
    1.03
    Activations Density 1.328%

    No Known Activations