© 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. 6469
    Prev
    Next
    INDEX
    Explanations

    financial and economic terms and information

    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
    +0.20
    0.9%
    604
    +0.14
    0.6%
    1842
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1385
    +0.20
    0.18
    1870
    +0.14
    0.07
    1499
    +0.14
    0.16
    Negative Logits
    <bos>
    -3.70
    ⓧ
    -1.34
    /***
    -1.19
     intersper
    -1.13
    
    -1.11
    <?
    -1.00
    /**
    -0.98
     disbur
    -0.89
    <?
    -0.86
    //*/
    -0.86
    POSITIVE LOGITS
     riva
    1.03
     bandung
    1.00
     marea
    0.94
     Muhamma
    0.93
     Jambi
    0.92
     Minang
    0.89
     Banjar
    0.89
     soulign
    0.89
     Palembang
    0.89
     epoca
    0.87
    Activations Density 3.761%

    No Known Activations