© 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. 885
    Prev
    Next
    INDEX
    Explanations

    text related to fandoms, love, and adoration expressed in the form of letters and symbols

    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
    1343
    +0.13
    0.5%
    50
    +0.09
    0.4%
    16
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.13
    0.13
    16
    +0.09
    0.09
    297
    +0.06
    0.07
    Negative Logits
    <bos>
    -2.05
     intersper
    -1.98
     encomp
    -1.76
     fta
    -1.73
     thut
    -1.69
     milf
    -1.67
     ftu
    -1.65
     fays
    -1.59
     disagre
    -1.57
     fuf
    -1.56
    POSITIVE LOGITS
     p
    0.68
     g
    0.66
     f
    0.65
     k
    0.64
     catég
    0.64
     F
    0.64
     b
    0.63
     G
    0.63
     c
    0.63
     t
    0.62
    Activations Density 0.752%

    No Known Activations