© 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. 12359
    Prev
    Next
    INDEX
    Explanations

    names of people or entities, likely related to a list or roster

    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
    1343
    +0.20
    0.6%
    906
    +0.12
    0.4%
    1403
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1003
    +0.20
    0.02
    888
    +0.12
    0.03
    1788
    +0.12
    0.02
    Negative Logits
    cería
    -0.54
    phylactic
    -0.50
     липня
    -0.49
     травня
    -0.49
    弹窗
    -0.49
    cción
    -0.48
     вересня
    -0.48
    choso
    -0.48
    SuccessListener
    -0.48
     квітня
    -0.47
    POSITIVE LOGITS
     écout
    1.16
     récon
    1.10
     vété
    1.08
     montrant
    1.07
     étrang
    1.06
     véhic
    1.06
     soulign
    1.06
     confé
    1.05
     clô
    1.02
     rassemble
    1.02
    Activations Density 0.176%

    No Known Activations