© 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
    3. Joseph Bloom · Initial Gemma-2B SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 0-RES-JB
    11. 2059
    Prev
    Next
    INDEX
    Explanations

    names of individuals

    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
    1937
    +0.10
    0.3%
    1339
    +0.08
    0.2%
    687
    +0.07
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1343
    +0.10
    0.03
    283
    +0.08
    0.01
    724
    +0.07
    0.02
    Negative Logits
    fortawesome
    -0.58
     both
    -0.57
    blanc
    -0.55
     voltou
    -0.54
     къ
    -0.54
     дори
    -0.54
    roidered
    -0.54
     turn
    -0.53
    발
    -0.52
    ündigt
    -0.52
    POSITIVE LOGITS
    rie
    2.57
    ries
    1.59
    RIE
    1.47
     emphat
    1.21
     Arie
    1.21
     oleo
    1.20
     fluo
    1.17
     swarovski
    1.17
     bordeaux
    1.16
     effe
    1.13
    Activations Density 0.169%

    No Known Activations