© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 1541
    Prev
    Next
    INDEX
    Explanations

    mentions of specific terms related to projects or procedures

    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
    313
    +0.13
    0.8%
    889
    +0.11
    0.6%
    50
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    765
    +0.13
    0.03
    889
    +0.11
    0.03
    1921
    +0.11
    0.03
    Negative Logits
    <bos>
    -2.61
    HasIndex
    -0.79
    HasColumnType
    -0.74
    /*++
    -0.72
    public
    -0.71
    SizeMode
    -0.67
    ღ
    -0.67
    <>
    -0.67
    lateinit
    -0.66
    addGroup
    -0.66
    POSITIVE LOGITS
     increa
    2.10
     maneu
    2.00
     impra
    1.93
     affor
    1.93
     inev
    1.88
     intermitt
    1.83
     depic
    1.81
     Juf
    1.79
     scrat
    1.77
     suscep
    1.76
    Activations Density 0.194%

    No Known Activations