© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 0-RES-JB
    6. 192
    Prev
    Next
    INDEX
    Explanations

    the word "one" in various contexts

    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
    +0.16
    0.7%
    1622
    +0.05
    0.2%
    382
    +0.04
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.16
    0.04
    1622
    +0.05
    0.04
    1874
    +0.04
    0.03
    Negative Logits
    <bos>
    -2.14
     serve
    -0.73
    /*
    -0.72
     continue
    -0.71
    public
    -0.71
    
    
    -0.70
    struct
    -0.70
    /**
    -0.70
    }{||
    -0.69
    ,
    -0.69
    POSITIVE LOGITS
     maneu
    2.15
     increa
    2.12
     affor
    2.11
     fta
    2.09
     guarante
    2.08
     stockholm
    2.08
     aen
    2.07
     lidl
    2.06
     squa
    2.04
     secon
    2.03
    Activations Density 0.171%

    No Known Activations