© 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. 14104
    Prev
    Next
    INDEX
    Explanations

    text related to personal experiences 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
    1110
    +0.09
    0.3%
    78
    +0.08
    0.2%
    1892
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1537
    +0.09
    0.04
    1285
    +0.08
    0.03
    1892
    +0.08
    0.03
    Negative Logits
     accompagne
    -0.65
     habet
    -0.64
    nachron
    -0.64
     renfer
    -0.58
     ejus
    -0.58
     löyty
    -0.57
     équipement
    -0.56
     laaj
    -0.56
     soutient
    -0.56
     pageNo
    -0.56
    POSITIVE LOGITS
     privilege
    0.93
     privileged
    0.80
     Privilege
    0.72
     fortunate
    0.70
     privilegio
    0.68
    privilege
    0.66
     blessed
    0.62
    blessed
    0.59
     privileges
    0.59
     opportunity
    0.57
    Activations Density 0.214%

    No Known Activations