© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 1007
    Prev
    Next
    INDEX
    Explanations

    references to rivers in geographical 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
    +0.09
    0.3%
    1404
    +0.08
    0.3%
    874
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1473
    +0.09
    0.04
    619
    +0.08
    0.03
    354
    +0.08
    0.03
    Negative Logits
    <bos>
    -1.38
    <?
    -0.69
     maintain
    -0.66
    /*
    -0.65
     ensure
    -0.64
    <?
    -0.64
    /**
    -0.63
    public
    -0.61
     fulfill
    -0.61
     realize
    -0.61
    POSITIVE LOGITS
     river
    1.62
     rivers
    1.44
     fluo
    1.43
     véhic
    1.41
     catég
    1.40
     Juf
    1.38
    Rivers
    1.33
     délib
    1.33
     bordeaux
    1.31
     affor
    1.31
    Activations Density 0.116%

    No Known Activations