© 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. 4893
    Prev
    Next
    INDEX
    Explanations

    mentions of universities, courses, academic programs, and academic-related information

    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
    663
    +0.18
    1.0%
    2004
    +0.16
    0.9%
    25
    +0.14
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1363
    +0.18
    0.04
    227
    +0.16
    0.06
    1328
    +0.14
    0.05
    Negative Logits
    <bos>
    -0.93
    ี
    -0.69
    ेत्र
    -0.64
    fjspx
    -0.63
    resizingMask
    -0.63
    flink
    -0.61
    Android
    -0.58
    DockStyle
    -0.58
    Datuak
    -0.58
    ApiModelProperty
    -0.57
    POSITIVE LOGITS
     OXFORD
    1.36
     increa
    1.24
     oxford
    1.21
     Oxford
    1.20
    Oxford
    1.18
     encomp
    1.17
     Simult
    1.16
     impra
    1.15
     inev
    1.13
     endom
    1.08
    Activations Density 0.719%

    No Known Activations