© 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. 2286
    Prev
    Next
    INDEX
    Explanations

    information related to various entities such as reviews, cities, temples, and governmental organizations

    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
    453
    +0.18
    0.7%
    50
    +0.17
    0.7%
    1419
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1419
    +0.18
    0.11
    924
    +0.17
    0.14
    1105
    +0.12
    0.07
    Negative Logits
     in
    -0.82
    ,
    -0.80
     on
    -0.79
    .
    -0.77
    和
    -0.77
    一
    -0.76
     to
    -0.76
     for
    -0.76
     don
    -0.75
    Nhưng
    -0.74
    POSITIVE LOGITS
     effe
    2.24
     stockholm
    2.23
     intermitt
    2.15
     wien
    2.15
     ?...
    2.08
     sappi
    2.07
     increa
    2.04
     maneu
    2.03
     noel
    2.03
     dispen
    2.03
    Activations Density 2.671%

    No Known Activations