© 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. 4228
    Prev
    Next
    INDEX
    Explanations

    temporal phrases indicating specific moments or instances

    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
    +0.30
    1.1%
    453
    +0.14
    0.5%
    1013
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2004
    +0.30
    0.05
    453
    +0.14
    0.05
    897
    +0.13
    0.04
    Negative Logits
    <bos>
    -2.09
    addComponent
    -0.66
    addLast
    -0.65
    setClass
    -0.64
    addPreferredGap
    -0.62
    AsUp
    -0.58
    log
    -0.58
    @
    -0.58
    void
    -0.58
    addGap
    -0.57
    POSITIVE LOGITS
     Minang
    1.69
     Keny
    1.69
     Juf
    1.60
     silikon
    1.54
     practition
    1.53
     maneu
    1.52
     emphat
    1.49
     Pekan
    1.49
     bandung
    1.49
     Hitam
    1.48
    Activations Density 0.393%

    No Known Activations