© 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. 539
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "manufacturing" with varying activations

    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
    950
    +0.11
    0.4%
    50
    +0.08
    0.3%
    1870
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    950
    +0.11
    0.04
    1381
    +0.08
    0.03
    573
    +0.07
    0.03
    Negative Logits
    <bos>
    -1.42
    
    -0.74
    <?
    -0.71
     also
    -0.68
    <?
    -0.67
     had
    -0.67
     here
    -0.67
     have
    -0.66
    find
    -0.66
     began
    -0.66
    POSITIVE LOGITS
     affor
    2.03
     wien
    2.01
     Manufact
    2.01
     aen
    2.01
     stockholm
    1.96
     increa
    1.95
     effe
    1.94
     eiffel
    1.91
     Juf
    1.91
     fatis
    1.90
    Activations Density 0.125%

    No Known Activations