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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 10-RES-JB
    6. 1714
    Prev
    Next
    INDEX
    Explanations

    date ranges and timelines

    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
    0.7%
    856
    +0.11
    0.4%
    1967
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    856
    +0.22
    0.05
    160
    +0.11
    0.06
    225
    +0.09
    0.05
    Negative Logits
    <bos>
    -2.60
    ⓧ
    -0.85
    rawDesc
    -0.77
    SourceChecksum
    -0.76
    Datuak
    -0.75
     autorytatywna
    -0.74
    verwijspagina
    -0.73
    wikidata
    -0.71
    BeginInit
    -0.69
     Roskov
    -0.66
    POSITIVE LOGITS
     lele
    1.60
     maneu
    1.49
     wien
    1.49
     hcm
    1.45
     daz
    1.43
     stockholm
    1.41
     ohr
    1.40
     aen
    1.37
     mef
    1.35
     jaya
    1.35
    Activations Density 0.300%

    No Known Activations