© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 10-RES-JB
    11. 500
    Prev
    Next
    INDEX
    Explanations

    terms related to romantic relationships and experiences

    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
    +0.16
    0.7%
    1276
    +0.12
    0.5%
    555
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1872
    +0.16
    0.02
    1105
    +0.12
    0.02
    1590
    +0.11
    0.02
    Negative Logits
    <bos>
    -2.48
    AsUp
    -0.75
     Roskov
    -0.71
    AutoScale
    -0.71
     ISNI
    -0.71
    mergeFrom
    -0.69
    extendable
    -0.67
    ///////////////
    -0.67
    SequentialGroup
    -0.66
    HasIndex
    -0.65
    POSITIVE LOGITS
     impra
    1.83
     maneu
    1.68
     increa
    1.65
     affor
    1.65
     scrat
    1.60
     strick
    1.58
     fortn
    1.56
     inev
    1.55
     Intere
    1.55
     impractica
    1.54
    Activations Density 0.083%

    No Known Activations