© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 15845
    Prev
    Next
    INDEX
    Explanations

    information about responses or lack of responses to requests or comments

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    453
    +0.14
    0.4%
    1150
    +0.13
    0.4%
    674
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1309
    +0.14
    0.03
    1151
    +0.13
    0.03
    1907
    +0.08
    0.03
    Negative Logits
     ecru
    -1.26
     swarovski
    -1.26
     bordeaux
    -1.13
     tricot
    -1.13
     broderie
    -1.10
     oleo
    -1.05
     nutella
    -1.00
     tupperware
    -0.97
     thermomix
    -0.97
     cæ
    -0.96
    POSITIVE LOGITS
     contacted
    0.71
     emailed
    0.64
    Conta
    0.58
     contact
    0.58
     requested
    0.55
     requests
    0.54
     email
    0.54
     nor
    0.54
     request
    0.53
     interview
    0.52
    Activations Density 0.125%

    No Known Activations