© 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. 4333
    Prev
    Next
    INDEX
    Explanations

    mentions of live broadcasts or real-time events

    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
    +0.26
    1.5%
    1872
    +0.10
    0.6%
    130
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1872
    +0.26
    0.03
    130
    +0.10
    0.03
    866
    +0.10
    0.02
    Negative Logits
    <bos>
    -3.07
     u
    -0.70
    HasAnnotation
    -0.70
     don
    -0.70
     got
    -0.69
     introduce
    -0.69
    filepath
    -0.69
    HasMaxLength
    -0.68
    MockBean
    -0.68
    ComponentModel
    -0.68
    POSITIVE LOGITS
     Juf
    2.19
     maneu
    2.18
     affor
    2.15
     disagre
    2.13
     unlaw
    2.11
     increa
    2.11
     Minang
    2.10
     impra
    2.09
     impractica
    2.08
     accla
    2.04
    Activations Density 0.041%

    No Known Activations