© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 12011
    Prev
    Next
    INDEX
    Explanations

    quotes or statements that are bold or impactful

    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
    2034
    +0.19
    0.6%
    674
    +0.19
    0.6%
    1150
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    878
    +0.19
    0.06
    1208
    +0.19
    0.05
    382
    +0.14
    0.05
    Negative Logits
     viciss
    -2.12
     maneu
    -2.08
     impractica
    -1.92
     shenan
    -1.91
     disagre
    -1.90
     unwarran
    -1.86
     lamborghini
    -1.86
     impra
    -1.86
     encomp
    -1.85
     increa
    -1.85
    POSITIVE LOGITS
     "
    1.16
     “
    1.12
    “
    0.99
     «
    0.96
     „
    0.95
    ↵↵
    0.93
    「
    0.93
     ”
    0.91
     ".
    0.91
    "
    0.91
    Activations Density 0.180%

    No Known Activations