© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 10702
    Prev
    Next
    INDEX
    Explanations

    narratives revolving around personal or professional growth and accomplishments

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1861
    +0.10
    0.3%
    1373
    +0.09
    0.3%
    1467
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.10
    0.07
    1013
    +0.09
    0.07
    2044
    +0.09
    0.07
    Negative Logits
     meis
    -1.78
     saar
    -1.77
     lele
    -1.72
     aen
    -1.71
     „,
    -1.66
     kram
    -1.66
     kasa
    -1.65
     uhr
    -1.60
     mef
    -1.59
     Intere
    -1.59
    POSITIVE LOGITS
     with
    0.73
     against
    0.72
     until
    0.70
     for
    0.68
     without
    0.67
     in
    0.67
     alongside
    0.67
     and
    0.66
     throughout
    0.66
     amid
    0.65
    Activations Density 0.740%

    No Known Activations