© 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. 1042
    Prev
    Next
    INDEX
    Explanations

    references to academic disciplines in the field of social sciences

    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
    313
    +0.09
    0.3%
    411
    +0.07
    0.2%
    1870
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1211
    +0.09
    0.02
    283
    +0.07
    0.01
    1696
    +0.07
    0.02
    Negative Logits
     jerked
    -0.67
     inaugurate
    -0.66
     heighten
    -0.66
     reaff
    -0.64
     mustered
    -0.63
     cooperated
    -0.59
     shivered
    -0.59
     forbade
    -0.59
     plundered
    -0.58
     ratify
    -0.58
    POSITIVE LOGITS
     Sciences
    2.30
     SCIENCES
    2.06
     sciences
    2.05
    Sciences
    2.00
    sciences
    1.81
    ciences
    1.38
     myn
    0.95
     catég
    0.94
     Wissenschaften
    0.91
     Kategor
    0.88
    Activations Density 0.190%

    No Known Activations