© 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. 2043
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software development and coding

    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
    876
    +0.34
    1.1%
    678
    +0.16
    0.5%
    227
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.34
    0.06
    876
    +0.16
    0.00
    981
    +0.15
    0.05
    Negative Logits
    <bos>
    -1.12
    Biografi
    -0.89
    TextAppearance
    -0.80
    UniformLocation
    -0.79
    MergeFrom
    -0.79
    URLException
    -0.78
     May
    -0.77
    Appellee
    -0.77
    RetentionPolicy
    -0.76
    Története
    -0.75
    POSITIVE LOGITS
     nutr
    1.88
     affez
    1.86
     scrat
    1.84
     compen
    1.79
     embodi
    1.73
     inev
    1.71
     dises
    1.71
     !...
    1.71
     deleter
    1.70
     pollut
    1.70
    Activations Density 0.203%

    No Known Activations