© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 6550
    Prev
    Next
    INDEX
    Explanations

    details related to measurements and weights, particularly in a comparison context

    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
    1385
    +0.14
    0.4%
    876
    +0.09
    0.3%
    1214
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    642
    +0.14
    0.03
    870
    +0.09
    0.03
    1837
    +0.09
    0.03
    Negative Logits
     protokol
    -0.74
     kram
    -0.73
     makro
    -0.70
     zyn
    -0.69
     jep
    -0.65
     variabel
    -0.65
     ohr
    -0.64
     kaos
    -0.64
     ria
    -0.64
     praktik
    -0.64
    POSITIVE LOGITS
     weight
    1.19
     Weights
    1.05
     Weight
    1.05
     weights
    1.04
     weighs
    1.03
    Weight
    1.03
     WEIGHT
    1.02
     weighing
    1.02
     Weigh
    1.02
    weight
    1.00
    Activations Density 0.195%

    No Known Activations