© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 889
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific types of health or medical conditions

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.0.hook_resid_post_16384_anthropic
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    348
    +0.07
    0.2%
    1043
    +0.07
    0.2%
    1690
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.07
    0.06
    1343
    +0.07
    0.12
    184
    +0.07
    0.05
    Negative Logits
     conges
    -0.58
    salty
    -0.56
     tslint
    -0.56
     shea
    -0.55
    queeze
    -0.55
     muco
    -0.54
     tymp
    -0.53
     spina
    -0.53
     survi
    -0.53
     testis
    -0.52
    POSITIVE LOGITS
     vns
    1.05
     gaily
    1.05
     thut
    1.03
     myn
    0.99
     :—
    0.98
     effe
    0.93
     Strukt
    0.93
     reft
    0.91
     silikon
    0.91
     perfon
    0.91
    Activations Density 0.776%

    No Known Activations