© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 4703
    Prev
    Next
    INDEX
    Explanations

    numeric patterns and references to rankings within a structured text

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    568
    +0.13
    0.7%
    50
    +0.12
    0.6%
    1705
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    568
    +0.13
    0.03
    144
    +0.12
    0.03
    1233
    +0.12
    0.03
    Negative Logits
    <bos>
    -2.45
    /**
    -0.76
     intersper
    -0.76
     disbur
    -0.74
    <?
    -0.73
     unve
    -0.71
    relenting
    -0.69
     rouse
    -0.69
     defray
    -0.68
     enshr
    -0.68
    POSITIVE LOGITS
     Metro
    1.42
    Metro
    1.37
     Met
    1.26
     metro
    1.23
     Metropolitan
    1.19
    metro
    1.19
     METRO
    1.17
    Metropolitan
    1.15
    Met
    1.15
    METRO
    1.06
    Activations Density 0.157%

    No Known Activations