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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 378
    Prev
    Next
    INDEX
    Explanations

    details about events, speakers, and series

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.29
    1.2%
    2034
    +0.10
    0.4%
    1156
    +0.06
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    262
    +0.29
    0.07
    138
    +0.10
    0.09
    1288
    +0.06
    0.09
    Negative Logits
    <bos>
    -2.00
    ⓧ
    -0.82
     jsPsych
    -0.74
    //{
    -0.69
    InjectMocks
    -0.69
    //}
    -0.69
    ///**
    -0.69
    ത്ത
    -0.67
    <?
    -0.67
    ੌ
    -0.67
    POSITIVE LOGITS
     maneu
    2.22
     reluct
    2.10
     accla
    2.01
     disagre
    1.90
     affor
    1.89
     Juf
    1.87
     shenan
    1.86
     strick
    1.86
     wherea
    1.85
     impra
    1.84
    Activations Density 1.434%

    No Known Activations