© 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. 10-RES-JB
    11. 2914
    Prev
    Next
    INDEX
    Explanations

    occurrences of presence and absence in relation to various subjects

    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
    +0.20
    0.7%
    581
    +0.12
    0.4%
    438
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    581
    +0.20
    0.06
    438
    +0.12
    0.06
    1592
    +0.12
    0.04
    Negative Logits
    <bos>
    -1.40
    stylers
    -0.55
     lots
    -0.49
     unify
    -0.48
    área
    -0.47
     amo
    -0.46
    //---
    -0.46
     endow
    -0.46
    //};
    -0.46
    engeance
    -0.46
    POSITIVE LOGITS
     purtroppo
    1.03
     sappi
    1.02
     poichè
    0.98
     Luglio
    0.92
     tramont
    0.91
     soggior
    0.87
     Giugno
    0.85
     gabri
    0.85
     venuto
    0.84
     succede
    0.83
    Activations Density 0.443%

    No Known Activations