© 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-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 2003
    Prev
    Next
    INDEX
    Explanations

    names of individuals or characters

    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
    1516
    +0.14
    0.6%
    1520
    +0.14
    0.6%
    1482
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    981
    +0.14
    0.04
    1177
    +0.14
    0.02
    1520
    +0.13
    0.03
    Negative Logits
    braith
    -0.49
     Moussa
    -0.48
    icleta
    -0.45
    leriyle
    -0.45
    ingeki
    -0.45
    Sucesor
    -0.44
    usleep
    -0.44
     Blaise
    -0.43
    emplares
    -0.43
    celona
    -0.43
    POSITIVE LOGITS
     Ker
    1.29
    Ker
    1.27
     ker
    1.16
     KER
    1.07
     Kernel
    1.05
     kernel
    1.05
     kernels
    1.05
     Tar
    1.04
    Tar
    1.03
     TAR
    1.01
    Activations Density 0.211%

    No Known Activations