© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 14083
    Prev
    Next
    INDEX
    Explanations

    references to groups or individuals

    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
    1806
    +0.14
    0.5%
    1265
    +0.13
    0.5%
    513
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1806
    +0.14
    0.03
    513
    +0.13
    0.02
    812
    +0.13
    0.03
    Negative Logits
     expéri
    -0.73
     fédé
    -0.72
     levis
    -0.71
     hina
    -0.68
     accél
    -0.63
     gius
    -0.62
     affez
    -0.61
     impieg
    -0.61
     vana
    -0.59
     délib
    -0.59
    POSITIVE LOGITS
     Individuals
    1.04
     individuals
    0.99
    Individuals
    0.96
    individuals
    0.90
     individual
    0.77
     Individual
    0.75
    Individual
    0.72
     INDIVIDUAL
    0.72
     individuo
    0.71
    individual
    0.69
    Activations Density 0.061%

    No Known Activations