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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1048
    Prev
    Next
    INDEX
    Explanations

    specific website URLs

    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
    1027
    +0.10
    0.3%
    1343
    +0.10
    0.3%
    926
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1027
    +0.10
    0.07
    1343
    +0.10
    0.07
    1871
    +0.07
    0.02
    Negative Logits
    ⓧ
    -1.31
    /**
    -1.29
    <?
    -1.05
    /*
    -1.05
    
    -1.02
    <?
    -0.93
     intersper
    -0.92
    /*++
    -0.89
     disambigu
    -0.87
     repress
    -0.83
    POSITIVE LOGITS
     silikon
    1.00
     maksi
    0.95
    ...");
    0.89
     kosme
    0.86
     keramik
    0.84
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.83
     kokos
    0.82
    ...');
    0.79
     alkoh
    0.78
     minimalis
    0.78
    Activations Density 0.423%

    No Known Activations