© 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. 14157
    Prev
    Next
    INDEX
    Explanations

    mentions of real estate properties, transactions, developments, and constructions

    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
    1013
    +0.20
    0.6%
    939
    +0.13
    0.4%
    1120
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    939
    +0.20
    0.07
    1013
    +0.13
    0.06
    1216
    +0.12
    0.04
    Negative Logits
     disreg
    -0.83
     emphat
    -0.81
     smtplib
    -0.79
     pymysql
    -0.77
     pessi
    -0.76
     michelin
    -0.75
     stickied
    -0.72
     downvotes
    -0.72
     catast
    -0.71
     subgoals
    -0.71
    POSITIVE LOGITS
     building
    0.60
     space
    0.57
     site
    0.57
     redevelopment
    0.55
     vacated
    0.54
     vacant
    0.54
     buildings
    0.53
     former
    0.53
     Independencia
    0.52
    <bos>
    0.52
    Activations Density 0.424%

    No Known Activations