© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13813
    Prev
    Next
    INDEX
    Explanations

    technical issues reported in a QA or testing context

    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
    876
    +0.19
    0.6%
    344
    +0.10
    0.3%
    1403
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2044
    +0.19
    0.06
    1415
    +0.10
    0.02
    194
    +0.09
    0.01
    Negative Logits
     alkoh
    -0.82
     Milán
    -0.80
     kalori
    -0.79
     seksi
    -0.78
     Meksiko
    -0.75
     Cristóbal
    -0.70
     Meksi
    -0.70
     Libros
    -0.69
     Palestina
    -0.69
     organik
    -0.68
    POSITIVE LOGITS
     troubleshooting
    1.01
     troubleshoot
    0.99
     exasper
    0.90
     Troubleshooting
    0.79
     solvable
    0.77
     diagnosing
    0.76
     infuriating
    0.73
     disreg
    0.72
     remedied
    0.70
     ennemi
    0.70
    Activations Density 0.617%

    No Known Activations