© 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. 2355
    Prev
    Next
    INDEX
    Explanations

    social etiquette and behaviors, particularly related to hosting visitors in a home setting

    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
    1553
    +0.14
    0.4%
    1150
    +0.10
    0.3%
    674
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1553
    +0.14
    0.08
    12
    +0.10
    0.04
    1675
    +0.09
    0.07
    Negative Logits
     accla
    -1.33
     embra
    -1.32
     secon
    -1.27
     fath
    -1.26
     squa
    -1.26
     depic
    -1.25
     reluct
    -1.24
     emphat
    -1.21
     increa
    -1.20
     wherea
    -1.20
    POSITIVE LOGITS
    <bos>
    0.95
     politely
    0.63
     polite
    0.62
     conversation
    0.61
     verbal
    0.61
    verbal
    0.58
     conversational
    0.57
     yourself
    0.57
     ask
    0.57
     subtle
    0.56
    Activations Density 0.863%

    No Known Activations