© 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. 4558
    Prev
    Next
    INDEX
    Explanations

    patterns related to numbered sets and mathematical structures

    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
    1108
    +0.15
    0.4%
    1343
    +0.15
    0.4%
    453
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1108
    +0.15
    0.05
    1988
    +0.15
    0.04
    730
    +0.09
    0.04
    Negative Logits
    OGND
    -0.56
     lot
    -0.56
    desertcart
    -0.53
     mere
    -0.51
    것은
    -0.50
    bewerken
    -0.50
     ver
    -0.49
    тивов
    -0.48
     charge
    -0.48
     едва
    -0.48
    POSITIVE LOGITS
     milano
    1.27
     dises
    1.22
     Ottobre
    1.16
     napoli
    1.15
     estrema
    1.15
     clio
    1.15
     tulum
    1.13
     artig
    1.13
     Luglio
    1.12
     tranquillo
    1.10
    Activations Density 0.094%

    No Known Activations