© 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. 181
    Prev
    Next
    INDEX
    Explanations

    text related to human resources (HR) and corporate information

    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
    169
    +0.08
    0.3%
    1806
    +0.08
    0.3%
    1691
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1691
    +0.08
    0.02
    652
    +0.08
    0.02
    1343
    +0.08
    0.02
    Negative Logits
    <bos>
    -0.64
     underval
    -0.62
     denounce
    -0.59
     mobilize
    -0.57
     replenish
    -0.57
     foresee
    -0.57
     defray
    -0.57
     intensify
    -0.56
     overtook
    -0.56
     rehabilitate
    -0.56
    POSITIVE LOGITS
     HR
    2.43
    HR
    2.33
    hr
    2.13
     hr
    2.07
     Hr
    1.92
    Hr
    1.71
     HRM
    1.25
    HRM
    1.19
    hrs
    1.08
    HRP
    1.08
    Activations Density 0.106%

    No Known Activations