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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 13926
    Prev
    Next
    INDEX
    Explanations

    information related to data encryption and mathematical concepts

    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
    876
    +0.16
    0.5%
    1499
    +0.13
    0.4%
    394
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1499
    +0.16
    0.08
    919
    +0.13
    0.03
    615
    +0.12
    0.04
    Negative Logits
     Salón
    -0.61
     Solidar
    -0.61
     kompati
    -0.57
     Darío
    -0.53
     Belén
    -0.51
     Weit
    -0.51
     Jó
    -0.51
     تضيفلها
    -0.50
     bodas
    -0.50
     Renée
    -0.49
    POSITIVE LOGITS
     perfon
    0.97
     xdrive
    0.91
     reft
    0.83
     tranf
    0.83
     ftu
    0.82
     pym
    0.81
     deere
    0.81
     increa
    0.80
     ftre
    0.80
     suscep
    0.79
    Activations Density 0.467%

    No Known Activations