© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 6513
    Prev
    Next
    INDEX
    Explanations

    references to education and business institutions, particularly relating to specific programs, schools, and disciplines

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.21
    0.8%
    1870
    +0.11
    0.4%
    490
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.21
    0.04
    203
    +0.11
    0.04
    547
    +0.08
    0.06
    Negative Logits
    <bos>
    -1.82
     disbur
    -0.63
     inaugurate
    -0.58
    ⓧ
    -0.57
     whistled
    -0.57
     jakarta
    -0.57
     shuddered
    -0.57
     winked
    -0.56
     jerked
    -0.56
     shivered
    -0.55
    POSITIVE LOGITS
     véhic
    0.89
     🤣🤣
    0.84
     Minang
    0.81
     🥲
    0.79
     délib
    0.79
     catég
    0.78
     pleins
    0.78
     Business
    0.77
     ados
    0.75
    undai
    0.75
    Activations Density 0.733%

    No Known Activations