© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 5292
    Prev
    Next
    INDEX
    Explanations

    terms related to biochemistry and medical conditions such as osteoporosis

    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
    2019
    +0.21
    0.7%
    50
    +0.15
    0.5%
    283
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.21
    0.10
    382
    +0.15
    0.09
    1959
    +0.14
    0.10
    Negative Logits
     dicendo
    -0.70
     parteci
    -0.67
     raccont
    -0.64
    Obrigada
    -0.63
    Și
    -0.63
    Parabéns
    -0.63
    <bos>
    -0.61
    Ótimo
    -0.61
    suporte
    -0.60
    Polecam
    -0.59
    POSITIVE LOGITS
     bandung
    1.29
     fta
    1.13
     aen
    1.11
     hcm
    1.09
     siena
    1.09
     lele
    1.07
     Juf
    1.06
     meis
    1.05
     makro
    1.04
     jaya
    1.04
    Activations Density 0.859%

    No Known Activations