© 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
    2. Joseph Bloom · Initial Gemma-2B SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 4853
    Prev
    Next
    INDEX
    Explanations

    strong negative language with connotations of shock or disbelief

    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.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1978
    +0.10
    0.5%
    1339
    +0.10
    0.4%
    900
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.10
    0.03
    1233
    +0.10
    0.03
    1742
    +0.10
    0.02
    Negative Logits
    <bos>
    -2.38
    ⓧ
    -0.71
    
    
    -0.64
     الرياضيه
    -0.63
    #![
    -0.59
     ISNI
    -0.58
     Ros
    -0.55
    /*++
    -0.54
    Extrait
    -0.54
    Cyfarwyddwr
    -0.53
    POSITIVE LOGITS
     maroc
    1.19
     Czechos
    1.16
     churrasco
    1.09
     paradiso
    1.07
     lorenzo
    1.05
     jorge
    1.05
     santiago
    1.04
     sergio
    1.03
     rodriguez
    1.02
     colombia
    1.00
    Activations Density 0.186%

    No Known Activations