© 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
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 3426
    Prev
    Next
    INDEX
    Explanations

    mentions of family relationships, particularly sons of 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
    1671
    +0.14
    0.5%
    1256
    +0.11
    0.4%
    169
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1671
    +0.14
    0.03
    1256
    +0.11
    0.02
    169
    +0.10
    0.02
    Negative Logits
     sufren
    -0.57
     cambian
    -0.51
     crece
    -0.50
     afectan
    -0.50
     trebui
    -0.50
     empiezan
    -0.48
     kasa
    -0.47
     ricordi
    -0.45
     conforman
    -0.45
     negozi
    -0.45
    POSITIVE LOGITS
     son
    1.25
     sons
    1.22
     Son
    1.20
    Son
    1.16
     SON
    1.10
     Sons
    1.05
    Sons
    1.03
    son
    0.94
     SONS
    0.90
    sons
    0.85
    Activations Density 0.061%

    No Known Activations