© 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. 968
    Prev
    Next
    INDEX
    Explanations

    dates and locations mentioned in a news article

    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
    1150
    +0.07
    0.2%
    202
    +0.07
    0.2%
    1730
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    491
    +0.07
    0.07
    1288
    +0.07
    0.07
    1891
    +0.07
    0.08
    Negative Logits
    <bos>
    -1.00
    
    
    -0.68
    ⓧ
    -0.66
    /**
    -0.58
    <?
    -0.57
    public
    -0.55
    InitStruct
    -0.52
     must
    -0.52
     IEnumerator
    -0.51
    static
    -0.50
    POSITIVE LOGITS
     Minang
    1.07
     maroc
    1.06
     dises
    1.05
     lidl
    1.05
     dott
    1.03
     signora
    1.01
     bambina
    1.00
     😭😭
    1.00
     carrefour
    0.98
     papà
    0.98
    Activations Density 1.047%

    No Known Activations