© 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. 377
    Prev
    Next
    INDEX
    Explanations

    references to the concept of the universe

    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
    687
    +0.18
    0.8%
    1602
    +0.12
    0.5%
    555
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1438
    +0.18
    0.02
    1602
    +0.12
    0.02
    687
    +0.12
    0.02
    Negative Logits
    <bos>
    -2.14
    żdy
    -0.68
     reaff
    -0.62
     renounced
    -0.56
     sell
    -0.56
     familiarize
    -0.56
     inaugurate
    -0.55
     sharpen
    -0.54
     manage
    -0.54
     retorted
    -0.54
    POSITIVE LOGITS
     universe
    1.17
    universe
    1.10
     Universe
    1.06
    Universe
    1.04
     rispond
    0.94
     kram
    0.92
     Lombar
    0.92
     vespa
    0.91
     Karang
    0.90
     alpes
    0.89
    Activations Density 0.207%

    No Known Activations