© 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. 383
    Prev
    Next
    INDEX
    Explanations

    references to a specific place or brand (Metro) and details related to it

    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
    568
    +0.10
    0.3%
    486
    +0.07
    0.2%
    555
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    568
    +0.10
    0.03
    2001
    +0.07
    0.02
    1120
    +0.07
    0.02
    Negative Logits
    <bos>
    -0.90
    /**
    -0.78
    <?
    -0.76
    <?
    -0.72
    ⓧ
    -0.69
    
    -0.66
     springfox
    -0.61
     contend
    -0.60
     renounced
    -0.58
     IActionResult
    -0.57
    POSITIVE LOGITS
     Metro
    2.13
    Metro
    2.10
     metro
    1.97
    metro
    1.76
     METRO
    1.68
     Métro
    1.51
    METRO
    1.39
     wien
    1.37
     métro
    1.36
     fte
    1.31
    Activations Density 0.185%

    No Known Activations