© 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. 12398
    Prev
    Next
    INDEX
    Explanations

    phrases related to movement and behavior in a group or system

    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
    674
    +0.10
    0.3%
    1013
    +0.09
    0.3%
    284
    +0.09
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    284
    +0.10
    0.06
    1081
    +0.09
    0.05
    985
    +0.09
    0.04
    Negative Logits
     ?...
    -0.86
     „,
    -0.86
     Cfr
    -0.83
     nece
    -0.81
     desir
    -0.81
     !...
    -0.80
     fte
    -0.79
     inev
    -0.78
     alre
    -0.77
     purcha
    -0.77
    POSITIVE LOGITS
     again
    0.67
     back
    0.55
     after
    0.54
     resumed
    0.53
    MLLoader
    0.52
    mybatisplus
    0.51
     later
    0.51
     cilindros
    0.51
     wieder
    0.51
    athione
    0.50
    Activations Density 0.329%

    No Known Activations