© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 6545
    Prev
    Next
    INDEX
    Explanations

    financial information related to stocks and companies

    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
    +0.26
    1.0%
    1385
    +0.07
    0.2%
    1253
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1891
    +0.26
    0.04
    1630
    +0.07
    0.06
    1852
    +0.06
    0.05
    Negative Logits
    <bos>
    -2.42
    ⓧ
    -1.11
    
    
    -0.99
    /**
    -0.95
     intersper
    -0.95
    <?
    -0.95
     inaugurate
    -0.79
     quitted
    -0.77
    /***
    
    -0.76
     disbur
    -0.74
    POSITIVE LOGITS
     catég
    0.82
     véhic
    0.82
     soulign
    0.81
     Muhamma
    0.74
     Bintang
    0.71
     Gnaden
    0.71
     épu
    0.70
     incontour
    0.69
     Minang
    0.68
     vieill
    0.67
    Activations Density 0.591%

    No Known Activations