© 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. 10-RES-JB
    11. 4205
    Prev
    Next
    INDEX
    Explanations

    references to various statistics and data points related to research findings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    chanind/openwebtext-gemma
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    1,024
    Dataset
    ctigges/openwebtext-gemma-1024-cl
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.22
    0.9%
    184
    +0.15
    0.6%
    1438
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1438
    +0.22
    0.07
    908
    +0.15
    0.05
    1553
    +0.13
    0.07
    Negative Logits
    <bos>
    -3.42
     encomp
    -1.35
    Autoritní
    -1.25
     autorytatywna
    -1.19
     eyel
    -1.19
     intersper
    -1.17
     sappi
    -1.11
     embodi
    -1.10
     scrat
    -1.10
     squa
    -1.09
    POSITIVE LOGITS
     bakar
    0.60
     kesi
    0.59
     StatusCode
    0.58
     kaos
    0.57
     kasa
    0.56
     maske
    0.55
    .
    0.54
     preventivo
    0.54
     despite
    0.54
    :].
    0.53
    Activations Density 0.571%

    No Known Activations