© 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. 14372
    Prev
    Next
    INDEX
    Explanations

    descriptions of actions and events

    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
    2019
    +0.28
    0.9%
    381
    +0.14
    0.5%
    304
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2019
    +0.28
    0.02
    623
    +0.14
    0.02
    1045
    +0.13
    0.01
    Negative Logits
     horrend
    -1.05
     snoopy
    -1.03
     gotcha
    -1.02
     stickied
    -0.98
     shenan
    -0.96
     pooh
    -0.95
     unavoid
    -0.93
     caucasian
    -0.92
     polaroid
    -0.90
     apportion
    -0.89
    POSITIVE LOGITS
     meras
    0.79
     keramik
    0.76
    Linki
    0.72
     antik
    0.70
     guir
    0.69
     abbiano
    0.67
     praktik
    0.66
    estimable
    0.66
     seksi
    0.65
     ideolog
    0.65
    Activations Density 0.072%

    No Known Activations