© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7313
    Prev
    Next
    INDEX
    Explanations

    operations related to memory management in programming code

    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
    453
    +0.27
    0.9%
    1042
    +0.20
    0.7%
    1871
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    453
    +0.27
    0.03
    1871
    +0.20
    0.03
    825
    +0.17
    0.02
    Negative Logits
     McLaugh
    -0.95
     Punj
    -0.91
     thunderbolt
    -0.89
     horrend
    -0.83
     gallows
    -0.83
     Aftermath
    -0.81
     Briton
    -0.79
     hatchet
    -0.78
     Glou
    -0.76
     murmuring
    -0.76
    POSITIVE LOGITS
     magis
    1.25
     maxime
    1.14
     albic
    1.11
     aquare
    1.09
     propter
    1.08
     vernac
    1.08
     menta
    1.06
     marte
    1.06
    izational
    1.05
     grati
    1.05
    Activations Density 0.058%

    No Known Activations