© 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 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. 11026
    Prev
    Next
    INDEX
    Explanations

    references to different levels within a system or hierarchy

    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
    390
    +0.17
    0.6%
    1602
    +0.14
    0.5%
    168
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    390
    +0.17
    0.05
    1602
    +0.14
    0.04
    168
    +0.13
    0.04
    Negative Logits
     unspeak
    -1.18
     encomp
    -1.12
     shenan
    -1.05
     intersper
    -1.04
     reluct
    -1.03
     apprehen
    -1.01
     indescri
    -0.98
     gaily
    -0.96
     inconce
    -0.95
     impra
    -0.94
    POSITIVE LOGITS
    level
    1.48
     level
    1.44
     LEVEL
    1.41
    Level
    1.41
     Level
    1.38
    LEVEL
    1.33
    levels
    1.29
     levels
    1.28
     Levels
    1.23
    Levels
    1.17
    Activations Density 0.100%

    No Known Activations