© 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. 0-RES-JB
    11. 1493
    Prev
    Next
    INDEX
    Explanations

    phrases related to family and loved ones

    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
    875
    +0.06
    0.2%
    1545
    +0.06
    0.2%
    1739
    +0.06
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.06
    0.09
    304
    +0.06
    0.03
    283
    +0.06
    0.01
    Negative Logits
     intersper
    -1.99
     encomp
    -1.88
     disagre
    -1.87
     reluct
    -1.82
     apprehen
    -1.82
     shenan
    -1.78
     vainly
    -1.71
     quitted
    -1.70
     increa
    -1.68
     disreg
    -1.67
    POSITIVE LOGITS
     poros
    0.78
     balon
    0.78
     teolog
    0.72
     sonda
    0.72
     marat
    0.70
    @[+][
    0.70
     asisten
    0.69
     Himo
    0.69
    providedIn
    0.69
     Seeder
    0.67
    Activations Density 0.796%

    No Known Activations