© 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. 12781
    Prev
    Next
    INDEX
    Explanations

    web URLs

    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
    468
    +0.11
    0.3%
    906
    +0.10
    0.3%
    1403
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.11
    0.04
    1937
    +0.10
    0.04
    1689
    +0.10
    0.04
    Negative Logits
    shadowOffset
    -0.75
    AddTagHelper
    -0.72
    shadowOpacity
    -0.64
    andReturn
    -0.62
    TableField
    -0.61
    RequestParam
    -0.59
    strokeWidth
    -0.58
    ComponentScan
    -0.58
    userdetails
    -0.58
    pageX
    -0.58
    POSITIVE LOGITS
     encomp
    1.45
     intersper
    1.41
     philanth
    1.40
     volunte
    1.39
     accla
    1.38
     reluct
    1.38
     impra
    1.30
     increa
    1.29
     guarante
    1.28
     resear
    1.28
    Activations Density 0.331%

    No Known Activations