© 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. 724
    Prev
    Next
    INDEX
    Explanations

    mentions of various locations or entities related to the United States

    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
    +0.13
    0.6%
    1978
    +0.05
    0.2%
    131
    +0.05
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1479
    +0.13
    0.05
    1360
    +0.05
    0.05
    270
    +0.05
    0.05
    Negative Logits
    <bos>
    -1.41
    ⓧ
    -0.81
    /**
    -0.77
    public
    -0.75
     continue
    -0.74
     also
    -0.72
     put
    -0.72
    
    
    -0.71
     serve
    -0.70
     keep
    -0.70
    POSITIVE LOGITS
     affor
    2.47
     maneu
    2.29
     increa
    2.24
     impra
    2.10
     embodi
    2.08
     disagre
    2.08
     excru
    2.05
     Juf
    2.04
     véhic
    2.03
     perfet
    1.99
    Activations Density 0.121%

    No Known Activations