© 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. 6602
    Prev
    Next
    INDEX
    Explanations

    numbered lists or items within a list

    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
    872
    +0.11
    0.3%
    919
    +0.10
    0.3%
    781
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    919
    +0.11
    0.04
    2030
    +0.10
    0.04
    1914
    +0.09
    0.06
    Negative Logits
     meis
    -1.12
     akut
    -1.11
     abnorm
    -1.09
     „,
    -1.08
     plak
    -1.07
     antik
    -1.07
     Kün
    -1.06
     stoff
    -1.03
     accla
    -1.03
     Departement
    -1.02
    POSITIVE LOGITS
    marginHorizontal
    0.53
    lcccccc
    0.50
    paddingVertical
    0.49
    toEqual
    0.49
    ítése
    0.47
    =('
    0.47
    Grüße
    0.46
    xFFFFFF
    0.46
    toBe
    0.46
    getHeight
    0.45
    Activations Density 0.772%

    No Known Activations