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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 4608
    Prev
    Next
    INDEX
    Explanations

    legal terms and copyright-related phrases

    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
    +0.19
    1.0%
    1870
    +0.15
    0.8%
    394
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1870
    +0.19
    0.11
    1385
    +0.15
    0.19
    1013
    +0.09
    0.20
    Negative Logits
    <bos>
    -3.72
     intersper
    -1.08
     acquaint
    -0.88
     harmonize
    -0.85
     endow
    -0.85
    /***
    -0.83
     disbur
    -0.82
     amass
    -0.78
     ratify
    -0.77
     defray
    -0.76
    POSITIVE LOGITS
     soggior
    0.99
     signora
    0.95
     bandung
    0.91
     montagna
    0.85
     pandan
    0.85
     ecru
    0.83
     Bekasi
    0.83
     lavable
    0.83
     paradiso
    0.82
     croce
    0.82
    Activations Density 5.083%

    No Known Activations