© 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. 12039
    Prev
    Next
    INDEX
    Explanations

    proper nouns and dates of birth

    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
    2019
    +0.20
    0.6%
    227
    +0.13
    0.4%
    950
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    950
    +0.20
    0.07
    1265
    +0.13
    0.05
    1376
    +0.13
    0.05
    Negative Logits
     عبدالله
    -0.59
     '/';
    -0.57
    embroidered
    -0.55
     "/";
    -0.54
     '-';
    -0.53
    就行
    -0.52
    wurde
    -0.52
    出错
    -0.51
    超时
    -0.51
    弹窗
    -0.50
    POSITIVE LOGITS
     keramik
    1.02
     optik
    0.98
     sovere
    0.96
     alkoh
    0.94
     inev
    0.91
     dises
    0.91
     inol
    0.89
     mikrofon
    0.89
     kosme
    0.88
     praktik
    0.87
    Activations Density 0.225%

    No Known Activations