© 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. 0-RES-JB
    11. 333
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Zion"

    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.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1053
    +0.08
    0.2%
    90
    +0.07
    0.2%
    2011
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    690
    +0.08
    0.04
    1363
    +0.07
    0.03
    1120
    +0.07
    0.04
    Negative Logits
     rubio
    -0.66
     osse
    -0.65
     disreg
    -0.63
    Ikr
    -0.62
     earnestness
    -0.61
     Ejercicio
    -0.61
     lanka
    -0.61
     weariness
    -0.59
    hésite
    -0.58
     obstin
    -0.58
    POSITIVE LOGITS
     Zion
    1.56
    Zion
    1.31
     penetration
    1.30
     Penetration
    1.26
     penetrate
    1.24
     penetrating
    1.13
     penetrates
    1.13
     penetrated
    1.13
     penet
    1.10
     Motley
    1.06
    Activations Density 0.293%

    No Known Activations