© 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. 0-RES-JB
    11. 390
    Prev
    Next
    INDEX
    Explanations

    mentions of laws or regulations being implemented or changed

    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
    +0.13
    0.6%
    732
    +0.06
    0.3%
    2011
    +0.05
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1625
    +0.13
    0.06
    462
    +0.06
    0.06
    1614
    +0.05
    0.06
    Negative Logits
    <bos>
    -1.67
    
    -0.99
    /**
    -0.92
    /*
    -0.85
    ⓧ
    -0.84
    public
    -0.83
    }{||
    -0.78
            
    -0.77
        
    -0.76
     continue
    -0.76
    POSITIVE LOGITS
     maneu
    2.40
     unden
    2.33
     affor
    2.32
     impra
    2.22
     accla
    2.21
     stockholm
    2.21
     increa
    2.16
     Juf
    2.14
     philanth
    2.10
     inder
    2.09
    Activations Density 0.127%

    No Known Activations